CA2118135C - Speech recognition system for electronic switches in a cellular telephone or personal communications network - Google Patents
Speech recognition system for electronic switches in a cellular telephone or personal communications network Download PDFInfo
- Publication number
- CA2118135C CA2118135C CA002118135A CA2118135A CA2118135C CA 2118135 C CA2118135 C CA 2118135C CA 002118135 A CA002118135 A CA 002118135A CA 2118135 A CA2118135 A CA 2118135A CA 2118135 C CA2118135 C CA 2118135C
- Authority
- CA
- Canada
- Prior art keywords
- mobile
- mobile unit
- mobile telecommunications
- voice
- unit customer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/18—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1853—Satellite systems for providing telephony service to a mobile station, i.e. mobile satellite service
- H04B7/18567—Arrangements for providing additional services to the basic mobile satellite telephony service
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M11/00—Telephonic communication systems specially adapted for combination with other electrical systems
- H04M11/10—Telephonic communication systems specially adapted for combination with other electrical systems with dictation recording and playback systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42204—Arrangements at the exchange for service or number selection by voice
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
- H04M2201/405—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition involving speaker-dependent recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
- H04W88/18—Service support devices; Network management devices
Abstract
An advanced telecommunications system is provided for the recognizing of spoken commands over a cellular telephone (15), satellite telephone (14), or personal communications network (16). In the cellular application, for example, a Speech Recognition System (20) interconnects either internally with or as an external peripheral to a cellular telecommunications switch (12). The Speech Recognition System (20) includes an administrative subsystem (21), a call processing subsystem (23), a speaker-dependent recognition subsystem (25), a speaker-independent recognition subsystem (27), and a data storage subsystem (29). Pre-recorded instructional messages are stored in the memory of the call processing subsystem (23) for instructing a user on his or her progress in using the system. The speaker-independent recognition subsystem (27) allows the user to interact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem (25). User specific attributes collected by the recognition subsystems are stored in the data storage subsystem (29).
Description
f''l~.j,.. . .., " ',...:'... ,...... ,:'~.. ., , .. . .. , .~..~r~ .. ,. ..
.. ...
,, r.. ::a PCT/~IS93/03491 '~.:.:::v WO 93/21721 _1 _ SPEECIi RECOGNITION SYSTEM FOR
ELECTRONIC SWITt~S IN A CELLULAR TEI~PgiONE
OR PERSONAL COMMUNICATIONS RETWORftC
This invention is related to telecommunications systems. and more particularly to an electronic digital signal processor-controlled telecommunications ystem for the recognition of spoken commands and for the directing of telephone calls based on spoken commands.
It is well--known that many of the safety hazards of cellular telephone use could be alleviated b~ utilizing automatic speech recognition. While telephone-based speech recognition systems are known, cellular voice dialing over a mobile telephone exchange ("MTX") presents significant challenges for two basic reasons.First; the recognition technology must accommodate a tremendous range of bath remotely-mounted and hand-held microphone types.
Second, the signal'may be band-limited and degraded in transmission to the MTX where the recognition system will be located. Voice-controlled dialers of the prior art. such as taught in U.S. Patent No.
4,x53,953 to Fujisakihave not been successfully implemented in the cellular environment.
There is therefore a-need for voice recognition systems for use in the Cellular; sattelite and and personal communications network environments that overc~cne these and other problems of the prior art and that facilitate the use of voice-dialing and other safety and convenience features.
It is therefore an object of the present invention to describe an implementation of a speech recognition system in a cellular or personal communications network environment.
It is a further object 'of the invention to describe a speech recognition.system for use at a mobile telephone exchange (MTX) of a cellular or personal communications network. The placement of . . . . ,~ ...W, . , ~ ; .~. . . . . . .. . . 4 , ~: ; W A_'... .' , , ,.~.. _ ~ . ~. ,.: ,':' , . ,~ '. , WO 93/2 ~ 721 ~ ~ 1 ~ ~ ~ a PCT/US93/03491 ~x . ': w , _2_ the speech recognition system at the MTX
significantly reduces cost and increases reliability by enabling the switch vendor to install and maintain the system in conjunction with the cellular switch. .
It is another object of the invention to describe a cellular voice dialing system for use in or in conjunction with an MTX of a cellular network.
It is still another object of the invention to use voice recognition techniques to secure access to a cellular ar personal c~mmunications network.
Another object of the invention is to provide for combined use of speaker-dependent and spea~Cer-independent voice recognition and speaker Z5 verification techniques,in an MTX of a cellular or pexsonal communications telephone network.
These and other objects of~the invention are provided in an advanced system for the recognizing of spoken commands over the cellular telephone or any personal communications (i.e., any non-wireline) network. In the cellular application., for example, a Speech Recognition System interconnects either internally witY~ or as an eternal peripheral to a cellular telecommunicati~ns MTX switch. TYae Speech Recognition System includes an'~dministrative subsystem, a call processing subsystem; a speaker-dependent recognition subsystem, a speaker-independent recognition subsystem, and a data storage subsystem. The Speech Recognz,tion 3Q Sys em also allows for increased efficiency n the cellular teleQhone network by integrating with the , switch ~r switches as a shared resource. 7che administrative subsystem of the Speech Recognition , System is used to keep statistical logs of pertinent call information. Pre-recorded instructional messages are stored in the memory of the call '' ~ ~ W~ 93121721 ~ ~ ~' ~ ~ ~ '~ PCfiUS93103491 processing subsystem for instructing a user on his or her progress in using the system. The speaker-independent recognition subsystem allows the user to interact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem.
User specific attributes collected by the recognition subsystems are stored in the data storage subsg~stem.
The foregoing has outlined some of the more pertinent objects of the present invention. These objects should be construed to be merely illustrative of some of the more prominent features and applications of the invention. Many other beneficial results can be attained by applying the disclosed invention in a different manner or modifying the invention as will be described.
Accordingly, other objects and a fuller understanding of the invention may be had by re~erra,ng to the following Detailed I3escription of the~preferred embodiment.
For a more complete understand~.ng of the present inven- tion and the advantages thereof, reference should be made to the following Detailed Descr~.Qtion taken in connection with the accompanying drawings in which:
FIGURE 1 is a bl4ck diagram o~ a cellular telephone network incorporating an external switch-based Speech Recognition System according to the present invention;
FIGURE 2 i.s a block diagram of a cellular telephone network incorporating an internal switch-based Speech ReCOgnition System;
FTGURE 3 is an upper level block diagram of the Speech Recognition System and data storage subsystem of FIGURE 1;
~...: , '.''. . ..:: :-.. .:::: ,','~',..... .':'..~.. ~~:,'.;.' ;~.~. ..;.:: -.:':~:.. .~..',': ..' .':.. .:., y.'.... '.:..:.:.'.~~:.... ,., , . ".,:., ...... .:~.. . .. ,~....... , '... .~ ;.. . :..,, ..
. ' . .':.. .:. .'. '. ,,. ....'. ......:r. : ~.. ..:."..'. .': ~ . :...~ ; '.
, ...
'.' .,y ...
1 ' 'rv . ......" "..., ,...~ .. '~.~.: ,. , , .°... o .:w.:w ..~;':.
'~::,~ , ....,,.' :'.:'n ..:., .,.,T. .,.,:,... . ~.. . ,;.,.:... :..;.:,..',.
,....~_.
Vt~O 93/21721 ~ ~ ~ ~ ~ ~ PCT/1JS93/03491.~;
FIGURE 4 is a detailed component diagram of the speech recognizer beard of the Speech Recognition System of FIGURES 2 and 3;
FIGURE 5 is a flowchart showing a Control routine used in the Speech Recognition System;
FIGURE 6 is a flowchart of the Dial routine of the invention used'by the subscriber to voice dial a telephone number that has been previously-stared by the subscriber;
~.p FIGURE 7 is a flowchart of the Call routine used by the subscriber to voice dial a speaker-independent telephone number;
FIGURE 8 is a flowchart of the Directory Dialing routine used by the subscriber to recall a previously-stored number using a speaker-dependent directory name;:
FIGURE 9 is a flowchart of a Store routine used to st~re subscrfiber'--specific destination number information;
FIGURE 10 is a flowchart of a lYtemory routine used to store speed-dial numbers associated with specific memory locataons,~ and FIGURE 11 is a flowchart of a Directory Storage routine used to store speaker-depenc7ent directory names and associated telephone numlaers for use by the subscriber to seed-dial destination numbers based on the associated directory names.
Similar reference characters refer to similar parts or steps throughout the several drawings.
FIGURE 1 is a block diagram of a cellular telephone network incorporating an external , switch-based Speech Recognition System according to the present invention. Although the following , description is.specifically related to use of the Speech Recognition Sgstem a~ or in conjunction with an MTX of a cellular network, it should be r ~: ° ~: v.':: ,.,.,;... ,...,.,;. .:.:'.,. ..;.:.. ,.;:v.. , ~.:~;, ~
..,..,,,... ,..~~:, , ., ,,'~,-: ~~. . . ..... .;-..... ~':~..:.~~ ...;
.::'... .
.i-.1...;.. . :,'~.: ... ..,~n."., .'..': ,:, ~.~. ,... .. . _:., , . .......
.. ~,.~,. :., .,.. ,...... :. ....: ~... ..
~..~:.,...~.........."...... . .... ~..'.~..-. .. , i..,', .~.;~... ~
.,;~:.,.,.. ..:'..'::.... ..:.,' ,;','.......,... , ..,...:. . r.~, ~
...".,...,".,... ~... ..
fr f... .,..........,...".~.-....., ' .......~.. . ".:-..... .. ..;~~..,., , '.'..;,'.,.. ~ ~ " .._.~~.., ..., ~. . . . ....
,. , . . . . . ' .,:.:.; ~. .......a... ,..."_._ .. . . .. . . .
WO 93/21721 PCTIEJS93/03~91 _5_ appreciated that the System also interconnects either internally with or as an eternal peripheral to a personal communications network. Indeed, the principles of the invention are applicable to any cellular-like network application, i.e., where a non=wireline communications network is employed for mobile, sattelite. portable or personal communications. The Speech Recognition System can also be used as a shared resource through integration with a plurality of such non-wireline communications networks.
Ref erring now to FIGURE 1, an exemplary telephone network is a cellular network 10 having a mobile telephone exchange (MTX) switch 12 connected to a transceiver and are antenna 14. The transceiver is located in each cell of the cellular network and c~mmunicates with the MTX to effect transmission and reception of signals to and from the mobile tel~ghone located in vehicle 15. The transceiver is typically connected to the MTX via a leased or dedicated network line 12. The MTX 12 is typically connected ~o the land-based destinations via telephone network 16.
A cellular molbile telecommunications system connects'mobile telecommunications customers. each having a mobile unit, to land-based customers served by a telephone network. Incoming and outgoing calls are routed through a mobile telecommunications switching: office connected to a group of cell sites that-communicate with mobile knits. The mobile telecommunications switching office includes a mobile telephone switching exchange (MTX) for routing the calls between the mobi7.e units az~d the telephone network. In a typicallg mobile cellular communacations system, there are usually many cells per MTX and several MTX's per system. ~s used .. ~, f rt ~ , ...:. .:: ,~ ,.' s ..~ ~.. "~ . ... . .. . .. .....
.,..,,,::' . . -. ~ ~ ., ~~; ....~.; . .v :: ~,~ -: : . .........
' . ..._,!~... . ~:~.~' ., ,:.; s: . . . ,.,~'' ., . w::.. .. ~ ~.~~,~ ~__ wr.~~ .,.>:: v,: - ~, ,. ...,. -' -~" ~'." ...
VNO 93/21721 ~ ~ ~ ~ ~ ~ ~ PGTILJS93/034~3 y herein, "mobile telecommunications system'° refers to both cellular, sattelite and personal communications network environments.
Each cellular telephone is uniquely identified by two numbers: a serial number ('°ESN") encoded in y the phone by its manufacturer, and a mobile identification number ("MIN"), which is the cellular telephone number programmed in by the cellular service provider. The service provider operates the MTX 12 and keegs a database of all MIN°s (and their associated ESN's)': Each time a call is placed by the cellular telephone; the service provider verifies whether the MIN and the associated ESN are aufihori.zed. If the MIN and ESN of a cellular phone are not recognized (and the area code or NPA of the MIN indicates that the phone number is outside of the provider's ervice area), the provider normally allows the call'to proceed at least one time. If billing authorization cannot later be verified, however, the MIN and serial number are then glaced on an ezceQtion Iist. Subsequent attempts to use the MIN will then be rejected:
According to one embodiment of the invention as shown in F'IGtJRE l, a Speech Rec~gnition System 20 is connected as an external peripheral to the MTX
through a set of preferably digital trunk lines.
'Set 22 is used for incoming signals and set 24 is used for outgoing signals. Other types of signaling, such as CEPT E1 or analog, may also be used besides T1. The Speech Recognition System 20 is connected to a dedicated data storage subsystem , 26 through a data network 28. The data storage subsystem is used to store recognition data derived , from the subscribers to the voice dialing service as will be described. The Speech Recognition System 20 may be integrated with one or more switches (whether ' WO 93/21721 Pi.T/US93/03491 or not cellular for use as a shared resource via incoming and outgoing trunk sets 30 and 32.
Referring now to FIGURE 2, a block diagram shows the cellular telephone network 10' with the Speech Recognition System 20 interconnected internally to the MTX. This is the preferred embodiment of the invention: The hierarchical architecture of the cellular switch includes the central processing unit 33; memory 34, data storage disk 35; cellular interface 36, central office trunk interface 37 and a backplane or switching matrix 38.
The Speech Recognition System 2Q includes a number of functional subsystems: an administrative subsystem 21, a call processing subsystem 23, a speaker-dependent recognition subsystem 25, a speaker-independent recognition subsystem 27, and the data storage subsystem 29 (which corresponds to the storage system 26 of FIGURE 1). The administrative subsXstem 2~. of the Speech 20.Re~ognition System is used to keep statistical logs of pertu nent call information. Pre-recorded 'instructional messages are stored in the memory of the call processing'subsystem 23 for instructing a usex on his or her progress in using the system.
The~speaker-independent recognition subsystem 27 allows the user to intexact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem 25. User sgecific attributes collected b~ trie recognition subsystems are stored in the data storage subsystem ' 29:
F3GURE 3 is an''upper level block diagram of the Speech Recognition System,of FLGURE 1. The hierarchical architecture of the Sgstem 20 comprises a control central processing unit 40, a speech ,._..i .:' '..:~...,i, .., ~;. ,. ;..:.: ~ . ,.~... > ,.,',. ......'v.-:.
.'.,. .. ... . ....;,.. .' ..': ,.,_. . ' :, .. .
... . ,., v v: .,.. ,....... .. . ..
.'.~ ' .,': '~ '..;.,. . :" ,. .,.. ;. ,_.., . . :~. : . , ~~... .:: -' ':': .
.:,-:': . . : ... . " ~. :'. ., ... ..., .
.. . .. ,.. ..
~Cw.2f. .. ,'. .... .... ... . ~ :' . . ..' , " . ',~ . ..., . ~... . ' ' ..
": ' ~ . ...:.. ' . ......
.Yn.'. ,.,:~.. :'.'...~,:<:...,.... ..,_ ......:. o.,.
WO 33/21721 PGT/US93/03491 .< w'.
~l~.g~~~
recognizer board 41, a video drive circuit board 42, a disk drive controller board 43 with associated hard disk drive, telephone interface circuit boards ' 44~ and a local area network ('°LAN") interface board 45. A local area network 45 connects these ' components of the System to the data storage subsystem 29, which comprises a LAN interface board 47, a CPU contro~1 board 48 and a mass storage hard drive device 49. As also seen in FIGURE 3. a pulse code modulation ("PCM'°) highway connects the telephone interfacevboards 44 to the speech recognition board 41. The MTX is also connected to the System 20 through the interface boards 44.
The CPU 40 and associated control programs l5 function a~ the'system administrative subsystem 21 of FTGURE 2. The recognizer board 41 acts as the recognition call p~oc~ssing subsystem 23 and the redognition subsystems 25 and 27. Command and control functions are communicated t~ the recogni~er board 41 from the system administrative processor 40 to the recognition call processing subsystem through a System bus. Responses received by the administrative processor from the recognition subsystem a.ndicate primary and secondary recognition responses, error codes and command acknowledgements.
Referring now ~o FIGURE 4, a more detailed schematic diagram is sh~wn of the recogni~er board 41 of FIGURE 3 and modules 25 and 27 of FIGURE 2.
The recognizer includes a control digital:~signal processor ('°DSP'° ) 'S0 having an associated memory 51 for supporting control programs anc3 data. The control DSP 50 in this embodiment of the invention controls a-plurality of sgeech recognition digital signal processors 52a...52d via a control bus 53.
The control DSP 50 also connects ~o an interface processor 54 via a host port interface 55.
WO 93/21721 ~ ~ ~ ~ ~ ~ ~ . PCT/US93/03491 _g_ Interface processor 54 has its own processor memory 56. A buffer 57 interconnects the interface processor to a system bus interface circuit 58 that interconnects the recognizer board to the system bus.
The PCM highway of FIGURE 3 or backplane of FIGURE 2 is connected to a PCM highway interface circuit 59 that supplies speech sample information to the control DSP 50 and memory 51 via address and data bases 60 and 61. Each of the speech recognition DSP's 52a...52d has an associated memory 62a:..62d and storage buffer 63a...63d. Buffered 'address and data buses 64'and 65 interconnect to the address and data buses 60 and 61 through the buffers 66.
The'interface processor 64 converts batch system commands or command blocks received through the system bus-interface 58 into singular commands for the'control DSP 50. Similarly, singular responses from the control DSP 50 are buffered by the interface processor 54 and are sent to the administrative processor (of FIGURES 2 and 3) in code blocks to increase overall system efficiency.
The control DSP 50 performs an active hybrid funotion which allows the speech secognizer to recognize commands spoken by the user while outgoing messa,g~s are being played: A11 telephone channel signaling and PCM highway sample transfer is handled by the control DSP 50 through the PCM highway interface 59. The cootrol DSP 50 is also used to perform an active hybrid function as well as to send samples and commands ~o the four speech recognition DSP's 52a...52ri. The control DSP 50 advantageously extracts incoming speech information even while speech prompts'or messages are being played by the system. Additionally; the DSP's 52 can recognize words spoken by the user while such speech is being n.- s r t ~d.~.S.
!.. . . ' i.:~
. .a. .., :T .~.'f . .. .1 .
~. 1.
f W~a .
.s E.
. .I~.'. . .5~.:
ln:..
S
h .
,..n.;:
l '. ~ 1 . .e X F
t ...a 1 < 1~ .
v 5.
S T
..;>S: _. ~..a .r.l r .. 1. .
.s .,.
.~ ~t.
,"'L_.v r u'y'~':' ~! r:.k ;: .,.y ~,..
..1., ::
t ...
y. .
f ~,: 2 . . ~.. y ~w~
S..
k . ...4". , ....
x>,..
._.> ~ ,.'t. 1 . .. ., ifl.h.., . ,. ~ ~,~aF~, ....~',~.hS, . ... .t , ,...,.... .~ 4~v . ,... .
W!.7;, , VlrO 93I2I72~ PCTItJS93l03491 <~-r~~...
tr,,.. f -lo-played by the system. Additionally. the DSP°s 52 can function to stop outgoing messages based on detection of certain incoming speech energy.
The system data flow is such that recognition commands and responses are sent to and from the ' administrative processor and the speech recognition DSP°s 52 through the control DSP 50, the interface processor 54, and the system bus interface 58.
Speech samples are received by the speech recognition DSP's 52 through the PCM highway interface 59 and the control DSP 50.
The present invention facilitates the implementation of voice-dialing in a cellular telephone or other personal communications netwark environment. When a-user "subscribes" to the service (e.g.: with the MTX service provider), it is desirable that certain speech data be collected from the subscriber for security purposes. Thuso upon subscription, the user normally will be asked to provide his or her'native language (e. g.. English Spanish; French; etc.). a personal identification number, and personal information related specifically to the subscriber such as a social security number or date of birth. This latter information may be used in an automated query process ass wili be described to prevent fraudulent use of the cellular or personal telephone network.
Once the user information is activated in the system, the user may place or receive telephone calls. Initia~.l~, the user will be required to enter speed-dial numbers and their associated da. rectory names .
Referring -now to FIGURE 5, a functional flowchart is provided describing the basic control functions of the Speech Recognition System according to the present invention. The routine begins at W~ 93/21721 ~ ~ ~ ~ ~ ~ '~ PC'f/ZJS93/03491 step 102 when the user dials digits from the cellular telephone. At step 104, a test is performed to determine if a Speech Recognition System access code has been dialed. Tf not, the cellular switch processes the call based on the number dialed at step 106 and the routine ends. If the result of the test at step 104 is positive, the routine continues at step 108 during which the switch makes an audio path connection between the user and the Speech Recognition System. At step 110, the switch sends the user's mobile identification number ("MIN") to the Speech Recognition System. As noted above. the M7:N is a unique number associated with a given cellular telephone that is available to the switch each time a telephone call is placed.
According to the invention, each user who subscribes to the service will have prerecorded a List of destina~zon numbers: At step 7.10. these speed-dial numbers, along with speaker-dependent emplates an:d user language type data, ,are retrieved from the data storage subsystem. As noted above, the data' torage subsystem stores such data at predetermined locations that are preferably accessed by the MIN: The routine then continues at step 17:2 with the Speech Recognition System prompting the user thatit is "Ready,For Command" or the like. The command is made in the language as determined by the user language type data retrieved at step 110. At step 114; the Speech Recognition Systems engages the speaker-independent recognition subsystem to obtain the user response. Depending on the response, one o'f several different subroutines follow.
If the user states and the system recognizes a "Dial" command, control is passed to the Dial ,~ v , ' :.~~. . . , ~ ~ ' ~ ,:~' -. :. ...,. ,.. , .,.. ~:.
s ~S ~.:- "~~.i . . ,. , , ~.,. .. ,... ..~ -.. ,. ,.., . . ,. .. .,., . .
WO 93121721 PGT/US93/03491 , ~ :~ ~. 8 ~. 3 ~ -12-Routine of FIGURE 6. In particular, a test is made at step 116 to determine if the Dial command is recognized. If so. control is transferred to the ' routine of FTGURE 6. If the response to the test at step I16 is negative, a test is made at step I18 to ' determine if a °'Call" connmand has been spoken and recognized. If the system recognizes a "Call"
Command. control is passed to the Call Routine of FIGURE 7. If 'the response to the test at step 118 ~.s negative, a test is made at step 120 to determine if a "Directory" command has been spoken and recognized. If the system recognizes a "Directory"
Command, control i~ passed to the Directory Dialing Routine of FIGURE 8.
~f the result of the test at step 120 is negative, a test is made at step 122 to determine if the user has spoken a ",Quit" command. If so, the routine terminates. If the result of the test at step I22 ~.s negative, the Speech Recognition System responds with a error message in step 124. A test is then performed at step 126 to determine if a predetermined maximum error count has been reached.
Tf not, control is transferred back to step 114. If the predetermined maxianum error count has been reached, the call and the MIN is transferred to an opexator at step 128 and the routine ends.
Referring now to FIGURE 6, the Dial Routine is described in detail. At step 130. the Speech Recognition System prompts the user with a message, such as "Phone Number Please," and applies the speaker-independent recognizer to collect the digits. A test is performed at step 132 to determine whether a digit has been collected. If not, a test is made at step 134 to determine if a predeterm~.ned timeout has elapsed. A negative response to the timeout step returns control back to x y t V us :. ~ s . .; ~~
~r ..,?.. ,. .., ,., . ~ '..~~ , . L.,.n . ,. xay . .., ,.... ,.
. z _13_ step 132. If the outcome of the test at step 134 is positive, the routine performs a test at step I36 to determine if at least the first digit of the phone number to be called has been entered. If so.
another test is performed at step 138 to determine if a maximum error count has been reached. If the outcome of the test at step 138 is negative, the Speech Recognition System promgts the user to "please enter nest digit"'at step 140 and control :returns-to step I32:
If, however, the outcome of the test at step 136 is negatives the routine tests to determine whether a maximum error count has been reached at step 142. If not. control returns to step 130 to request the user to enter the,phone number. If the outcome of the test at either step I38 or 142 is positive, the call (with the MIN) is transferred to an ogerator at step 144 and the routine ends.
If the outcome'of the test at steg 132 is positive, the recognizes preferably responds with a short beep'or other.audible indication at step 146.
.A test is then made at step 148 to determine if the digit collected'is the last digit expected in the string. If not:, the digit is saved'in a-string buffer at step 149 and the routine returns to step 132 to collect''another digi . If, however, the oui~come of step 148: is positive: all digits have been collected and he speaker-independent recognition subsystem is engaged at step 150.
At step 152, the subsystem attempts to verify the called number. If the verified ion command is not recognized, the Speech Recogniirion System responds at step 154 with a message such as "Error, Please repeat," and control returns back to step 152. If the outcome of the test at step 152 is positive, the telephone number is repeated to the ... . . ... . , .,... , . ,..,. . . . , ., . ..,." .a..,:... ~. .
WO 93/21721 ~'CflLJS93103491 ~"'~, user at step 156 and the speaker-independent recognition subsystem is engaged.
A test is then made at step 158 to determine ' whether the user (by spoken command) desires to "Store'° the number. If yes, the control is ' transferred to the Store routine of FIGURE 9. If the outcome of the test at step 158 is negative, a test 162 is made to determine whether the user has spoken (and the recogni~er has recognixed) a "Send"
~.0 command: If not, the Speech Recognition System again plays an error message at step 164 and control ~,s returned to step 158. A positive response to the "Send" test made at step 162 transfers the MIN and the string dialed to the switch for outdialing.
Such transfer occurs at step 166. At step 168, the switch dials the telephone number and connects the user to the dialed nbmber.
The Call routine is shown in detail in FIGURE
7: The routine begins at step 170 during which the Speeclh Recognition System responds to the user's "Call"' command with a message "Calling." At step 172, the speaker independent recognition subsystem is engaged to obtain the user°s response. A .test is then made at step ,174 to determine if the user spe~k~ a "Memory.' command; indicating that the number to be called is to be stored and made available for speed--dialing once a preferably two digit memory i~cation number is subsequently received. If the outcome of the test at step 174 is positive, the Speech,Recognition System queries the user °'Which memory" and engages the'recognition subsystem at step'176. At step 178: a test is made ~a determine if a two digit memory location has been identified by the user. If a two digit memory location-has not been'identified, a timeout test is performed at step 180. If timeout occurs, the ,: . ::: . .: . ," ..: ... ,... . .,,. ,; . .. . . . ..;, .
_ _ . ..
. : . : .... ~ -:. .. .~. ~ _ -; , : .... . . ; :.: . . : ,;;,.
r . .,. . .: .:~: : . . -::. ... v::: ,:.., .. .. . ,; ,, ~:: .; :,: ,~.,;e:
... ... ; .: -:.,. . ':. :. ., ,. . ,. .. ,._: " ... ..:. ..:: .. : :...:..., . ;: . .: , :. , . ,. . . ., ... .::'; ... ~ . ....
:."
~;,::~:: r:;:. ..:.~..:r.~,., : ~.:~..; .... ~.. .-.~. .,:. ,..."~. .:,....
..,.... .:.............:. ....,. . '~......,...... ~..::w.;..: ......:. ~..
..:>..:w..:,,...,." .,........ ...,..
5' ~, ;'. . .. . . , C, 'riv~ .. . . . ~.., ~ ... . . ..
':-,._- .. .. :.: r: ~. .~., .. . ... . - . . , ......, . . .... .
f..<~~.~:;.~, WO 93f21729 PCf/US93103491 Speech Recognition System prompts the user to °°Please enter newt digit" at step 182 and control is returned to step 178. A negative outcome of the timeout test also returns control back to step 178.
A posative outcome of the test at step 178 indicates that the two digit memory code has been received: The routine then recalls the previously-stored telephone number associated with the memory code at, step 184. The Speech Recognition System then notifies issues a "Calling" message to the user,at step X86.
A user may also retrieve the stored telephone number by speaking one of the speaker-independent key words. Thus, if the outcome of the test at step 174 is negative, the routine continues at step 187 with the user speaking a valid key word associated with one or more previously-stored telephone numbers. Without limitation, such key words include HOME, OFFICE, TI1KE, ' SECRETARY, FRIEND, ~rIORK and rINFORMATION. A test is then made at step 188 to determine if the work spoken is a valid key word.
If not: the system xesgonds with an error message at steps 190 and asks the user to speak the word again at steQ 1~7. A gositive outcome to the test at step 188 transfers control to step 186.
At step 192, the speaker-indepe~adent subsystem is again engaged to obtain a user command. A test is made at step 194 to determine whether the user desires to "Verify" the number retrieved. If a 3a "Verify" command is spoken and recognized, the s~bred number associated with the key word is repeated to the user and the recognizer is engaged at step I96. A test is then made at step 198 to determine whether he user desires to "Clear" the number retrie~red and start again: If so, the Speech ~~t'>.,::,.. .. ...': ,~, , .,. ~..,..,'. . . ~ ., .,., "... .,.. .'': . . .
WO 93/ZI721 FGT/US93/03491;.«'"
~I~~~~~ --16-Recognition System responds with a "Ready" message at step 200 and control returns to step 187.
If, however, the ~utcome of the test at either ' step 194 or step 198 is negative, a test is made at step 202 to determine if a "Send" command has been ,' spoken and recognized. If not, the system responds with an error message at step 204 and returns to step 192. If the user speaks the "Send" message, the Speech Recognition System responds at step 206 with a "Dialing" message. At step 208. the System transfers the MIN and the telephone number to be dialed to the Switch for outdialing. The switch dials the telephone number ana connects the user to the dialed number at step 210.
1S Referring now to FIGURE 8, a flowchart is shown of the Directory Dialing routine. This routine is called'when the user desires to recall and dial some previously-stored telephone numbers using a previously~stored speaker-dependent name. In response to'the "Dir.ectory" command from the user, the routine plays a message at step 212 to request the name in the directory. Step 212 also engages :the speaker-dependent recognition subsystem. A test is then made at step 214 to-determine if the name has been collected from the speaker. If no response is obtained. a timeout test is performed at step 2L6. Failure of the speaker to respond before the end of the timeout causes the issuance of an error message at step 218,and the routine.returns to step , 214. If the timeout occurs without the speaker's respanse, control is transferred back to step 212.
A positive outcome of the test' at s e~ 214 means that the directory name spoken by the user has been recognized. The routine then continues at step and recalls from the data storage subsystem a number associated with such name: At step 222, the S P
. , ,...':.1 ,.. ~'. ';. ~;. ~. ~ ;) .,~ ... . . . ~ ,. ~ . ..... ,....
a '...!' ..: S .. ..
i . 1 ..
r~:.:
..Vt .-: \ -a: 1..., .. ......,~.St~~ .. . . , .. ;..~~ ......... ,... >.x . ." ,.., ...,.... _ ..,.... ,. , C,ty...n...., . . .....,. , . ... ..
W~ 93/21721 , ~ ~ ~ ~ ~ ~ '~ PCf/Z.JS93103d91 -:. .:: ,;
stored number is played to the user and the Speech Recognition System issues a "Correct" prompt. A
test is then made at step 224 to determine if the number is correct. If not, control is returned back to step 212. If the outcome of the test at step 224 is positive. then the Speech Recognition System ' responds with a ''Dialing" message at step 226. At step 228, the System transfers the MIN and the telephone number to be dialed to the switch for outdialing. The switch dials the telephone number and connects the user to the dialed number at steg 230.
Referring now to the Store routine FIGURE 9, a flowchart is shown of a routine used by the 15' subscriber to store telephone numbers for the two digit memory codes, keywords, and directory names to be later dialed. The routine begins in response to receipt of a speaker'-independent ''Store" command spoken by the user to update the speed-dial list whenever necessary. At step 232, the routine responds to the command with a "Storing°' message and engages the speaker-indegendent recognition suk~system. A test is then made at step 234 to determine whether the user desires to store twa digit memory codes. If so, control is transferred to the Memory routine of FIGURE 10. If the outcome ofthe test at step 234 is negative, a test is made at step 236 to determine whether the user desires to store a Directory name or a number associated with a Directory name. If so, control is transferred to the Directory Storage routine of FIGURE 11. If the outcome of the test at step 236 is negative, then the system will'expect to receive a key word for association with the number to be stored at step 238. A test is thus made at step 240 to determine whether the subscriber has spoken a valid key word.
~' v »'a ~.., '.°.-:. . .. C4 y . , . . . .. ..,. .. ....... .. . . .,- .. .
...r..
W~ 93/21721 ~ . ~ PCT/US93/m3491 ~1~~~3~
If not, the system responds with an error message at step 242 and control is returned to step 234. Tf the outcome of the test at step 240 is positive, the ' Speech Recognition System makes an inquiry "Storing (key word), correct" and engages the ' speaker-independent recognition subsystem at step 244. A test is then made at step 246 to determine if the user selection is correct. If not, the Speech Recognition System issues a "Location, please" prompt at step 248 and returns to steg 240.
A positive outcome of the test at step 246 causes the system to issue a "Storing" prompt while a number associates with the keyword is stored in the data storage subsystem in step 249. Control is then returned to step 112 in FIGURE 5.
The Memory routine is shown in FIGURE 10. The routine begins at step 2~0 by inquiring '°'Which memory" and'engages the speaker-independent recognition subsystem. At step 252, a test is made to determine if a two digit memory location number has been collec ed from the user. A timeout test is then performed at step'254. If timeout occurs, the Speech Recognition System prompts the user to "Please enter~nezt digit" at step 256 and control is returned to step 252. A negative outcome of the timeout test also returns control back to step 252.
A positive outcome of the test at step 252 indicates that the two digit memory code has been collected from the subscriber. At step 258, the Speech Recognition System responds with a message "Storing memory (2 digits), correct" and emgages the speaker-independent recognition subsystem. A test is then made at step 260 to confirm that the subscriber is storing the telephone number in the appropriate location. If not, the Speech Recognition System issues a "Location, please"
,., ...6°...': .';; s .,. " ,-; ..-. ..-.....
.~:v:~:;:°:,:;:~, , ..:....,... ,,.. ., .... . .. :.y. . ~...,.:~.~,.
...~:.:':. ~. ~. .~:. :: ..:,!~ ,.., ~.., .... ~.~.~.,;.. ... ~ ..n.~.~:::~.
,:~.....a::.~...:...'. . ..
'.'.,°,' .:iw°, . .. ....,..
r.,.: ~ r;:~ . ...';;5. ...,. ~ . ......
. , .1..... . . .. , .,. .. ... . ., .. . .....
s,;...,., w0 93/21721 PCT/US93/~3191 _lg_ prompt at step 262 and returns to step 252. A
positive outcome of the test at step 260 then causes the routine to test at step 264 whether the memory is already filled up with stored codes. If not,..the system issues a "Storing" message and stores the number in the data storage subsystem at step 265.
If, however, the response to the test at step 264 is affirmative, the Speech Recognition System issues a "Memory full, erase?" message and engages the speaker-independent recognition subsystem at step 266: A testis then performed at step 268 to c7etermine whether the speaker wishes to erase a memory location: If not, control returns to step 112 in FIGUR& 5. , 1~ If the subscriber desires to erase a given memory location code, the system issues a "Confirm ~r,~se'i message at step 270 and engages the speaker-independent recognizer. An erase test is then gerformed again at step 272 to confirm that the 'subscriber wishes to.erase the specified memory location. A negative outcome of the test at stag 272 returns cohtrol to step I12 in FIGURE 5. A
positive outcome of the erase test at step 272 causes the system o issue an acknowledgment at step 274: Control then returns to step 112 in FIGURE 5.
Referring-now to FIGURE 11; a flowchart is shown of the Direct~ry Storage routine. The routine begins at step 276 in response to a positive response to the Directory inquiry performed in step 236 in FIGURE 9 (i.e:, receipt of the Directory dommand): Step 276 issues a prompt to the subscriber to determine if a "Number in Memory" has been previously associated with a Directory name. A
test is then performed at step 278 to determine if the Number in memory has been previously stored. If not, the Speech Recognition System responds by WU 93/21721 ~ ~ ~ PC~'/US93/03491 ~~ ~.~~. i~ -20-issuing an "Enroll" message and engages the speaker-independent recognition subsystem at step 280. A test is then made at step 282 to determine whether the subscriber wishes to enroll. If not, the routine terminates and returns to step 112 in f'IGURE 5.
If the outcome of the test at step 278 is affirmative, the Speech Recognition System issues a message "Re-enroll" and-engages the l0 speaker-independent recognition subsystem at step 284. A test is then made at step 286 to determine whether the subscriber wishes to re-enroll the directory name. If yes, or if the outcome of the test at step 282 is positive, the routine continues a~ step X88 and issues a HName Please" message and engages the speaker=dependent recognition subsys em. The user then speaks the name a predetermined numbex (e: g., three (3) times) at step 290 to program the speaker-dependent subsystem. The new directory name and the associated telephone ,number are then'stored in the data storage subsystem in step 292. Control is then returned to step 112 in FIGURE 5:
If the outcome of the test at step 286 is negative;'the Speech Recognition System issues a message "Erase°' and engages the speaker--independent recognition subsystem at step 296. A test is then made at step 298 to determine whether the subscriber wishes to erase the directory number. If so, the associated number is erased at step 300. Control is thea~ returned to step 112 in FIGURE 5.
It should be appreciated that tk~e specifis names of the commands are merely exemplary and .
should not be taken by way of limitation. Other suitable command ra~mes are of course suitable.
. ..:: . .~:~ . . ....:... .. ;. a . . . .: . ... . :~ : , ; :: ''';.:: :. ' ':~.,.. :.:; .;.:.
t~.x~ . . . . . :. ; , .. . .. , ........ ... .. .,... , .
dV0 93/23721 ~ ~ ~ ~ ~ PCT/US93l03491 _21_ As noted above, each cellular telephone is uniquely identified with its MIN and ESN. In the prior art, the service provider operates the MTX 12 and keegs a database of all MIN's (and their associated ESN's): Each time a call is placed by the cellular telephone, the service provider verifies whether the MIN and the associated ESN are authorized: If the MIN ana ESN of a cellular phone are not recognized in the switch database, the provider normally allows the call to proceed at least one time, If billing authorization cannot later be verified, however, the MIN and serial number are then placed on an exception list.
Subsequent attempts to use the MIN will then be 1.5 rej acted .
Such fraudulent use of the cellular network is ameliorated by the present invention. According to another feature of the invention, the Speech Recognition System also includes a positive idbntification function that enables the system under certain circumstances to test whether the user ~assaciated vrith a received MIN (whether in or out of the service area) is an authorized subscriber to the service. For ~egamgle; after a call is voice-dialed and the Send command is spoken, the system might prompt the caller to answer one or more personal quest~.ons. Thus, the caller might be requested to speak the social security and%or account number of the-subscriber (purportedly associated with the MIN
and ESN). Alternatively, the caller can be prompted ~o enter such identifying information manually through the telephone keypad. Of course. the nature and scope of the personal information requested by the system depends entirely on the system operator 3~ and the degree of security sought by the subscriber and operator.
V6~~ 93/21721 PC'TIUS93/03491': '"
~~~~8~_3~
Such a system could also be used to prevent a local call being placed from a stolen vehicle, for example, i.e., even if the MIN was recognized in the service provider's database. It could also be used to limit access to the voice-dialing function from ' the subscriber's phone to certain persons. Thus the subscriber may limit his or her children or others from using the phone without the subscriber's knowledge. If the user cannot provide proper answers to such questions, he system rejects the SEND command and the call is terminated. Correct entry of the requested information enables the caller to continue hi or her access to the service.
Alternatively the identification function may be implemented in conjunction with a speaker verification function in which the user's identity must first be verified with some spoken predetermined personal identification code. If the verification function is not 'convinced" that the person is wha he or she claims to be, the identification function is then executed to ask the follow-up questions. One such system is described in copending ~pPlication Serial No. 07/523,486, filed May 15, 1990. to Hunt et al, titled "Simultaneous Speaker-Independent ~'c~ice Recognition And Verification Over A Telephone Network,' assigned to the assignee of'the present invention.
The present invention had numerous advantages over the prior art. The system combines the use of bo1~h speaker-dependent'and speaker-independent speech recognition in an mobile or portable telephone communications network environment.
Multiple language prompts are spoken'from and available simultaneously on.multigle ports from a single automated telecommunication -based system.
The language selected is based on the language ~ - :. : , : y::., - : ,: . :.
c , ,, , ;:, : , . . ~ =. . ': : v'' . . : . .
,:
F.. ~
. ~c.. .. '. v ..
.v v .,..." r . . ." 4.,. , ,. :;,. , ., - , ": :: , v : ; ,. : ; .. :, w ' ;.:,.:
. '..
3 . 7 .. ). ..
.,., ~ ....,...,.a:.,....... t.. ~ .:. '..':: ..., .. ..
i ',...:. . . .. : : ... . ~ :: , : : . ~ : ~ ..,: . :, . ::: ~ ,~: :' a ..,...:: . . r .;....., ,.a .: _. ,~. .. . ..:.. ~.. . ~: .. ~ . :.' ~ . . , '., '. :~ ' :.. .. ,. , ~'u , . a~..:., ,:.:,.<~:~:.; .i~.'..!f. ., '~,.'~: .. ,.v::i.~.! ....., ~:. .
....,.. .:',.'~':. ,~..w,w, ~.,.',~~..,.. .n ..:..:.:' .. '..~. ~ ..... ...,.
..., . . .. . ..
WO 93/21721 ~ ~ ~ ~ ~ ~' ~ PCTlUS93/Q3491 ,. -23-spoken by the user. The system advantageously stores user specific speaker-dependent and speaker-independent speech information with particular user-based addresses.
The invention successfully implements speech recognition in the cellular telephone or personal communications network. Non-wireline networks provide a special challenge to both the recognition algorithm developers as well as the applications developers. The recognition algorithm in conjunction with the system application is insensitive to the radio fading, speech clipping, and speech compression conditions that occur in a non-wireline network: In addition, the recognition 1.5 algorithm accommodates conditions found in the standard-switched network. The invention provides a means ~f accurately recognizing speech that has l~,m;ited distortion'' due to clipping or fading and provides a means of reprompting the user for input when the speech has become too distorted for accurate recognition.
Previously, onlg the best examples of spoken words have been used as tokens for developing speech vocabularies. ~y collecting speech that has been compressed or that although distorted by radio fading or clipping is still intelligible and by adding this collected speech to the speech training database the vocabulary based on such data becomes more robust and Iess sensitive to these conditions.
Adding the distorted but intelligible data to the training database'of excellent example words allows for a more diverse statistical representation of each vocabulary word. Words that might have been previously rejected: because part of the word was clipped can now be recognized if enough intelligible information is available. If the statistical dV0 93/21721 PCT/US93/03491 :'"
:z:
~~~.~~3~
representation of the word indicates that not enough information is available for accurate recognition, the recognition system will reject the word and ' reprompt the user for input.
The invention also enables real-time vocabulary uploading. Previously, speech recognition vocabularies were stored in memory and were not updated or totally changed during the operation of an application: The present invention solves the lp problem of allozaing speech recognition vocabularies to be loaded into a recognition system while an application is in operation. This capability allows for less high speed memory to be used in a system, because an entire set of vocabularies is not required to be resident in memory at one time. This capability also allows for efficient memory management zahen multiple languages are used, because onllr the language required by the system user need be resident in memory at any one time. Previously, zp all possible languages required by users would have been stored in memory simultaneously.
Both continuous and discrete recognition techniques ire used in the Speech Recognition. System of the present invention.
It shQUld be appreciated by those skilled in the ark that the specific embodiments disclosed above may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present invention. It should also be realized by those skilled in the art that such equivalent constructions do not depart from the spirit anc3 scope of the invention as set forth in the appea~ded Claims:
.. ...
,, r.. ::a PCT/~IS93/03491 '~.:.:::v WO 93/21721 _1 _ SPEECIi RECOGNITION SYSTEM FOR
ELECTRONIC SWITt~S IN A CELLULAR TEI~PgiONE
OR PERSONAL COMMUNICATIONS RETWORftC
This invention is related to telecommunications systems. and more particularly to an electronic digital signal processor-controlled telecommunications ystem for the recognition of spoken commands and for the directing of telephone calls based on spoken commands.
It is well--known that many of the safety hazards of cellular telephone use could be alleviated b~ utilizing automatic speech recognition. While telephone-based speech recognition systems are known, cellular voice dialing over a mobile telephone exchange ("MTX") presents significant challenges for two basic reasons.First; the recognition technology must accommodate a tremendous range of bath remotely-mounted and hand-held microphone types.
Second, the signal'may be band-limited and degraded in transmission to the MTX where the recognition system will be located. Voice-controlled dialers of the prior art. such as taught in U.S. Patent No.
4,x53,953 to Fujisakihave not been successfully implemented in the cellular environment.
There is therefore a-need for voice recognition systems for use in the Cellular; sattelite and and personal communications network environments that overc~cne these and other problems of the prior art and that facilitate the use of voice-dialing and other safety and convenience features.
It is therefore an object of the present invention to describe an implementation of a speech recognition system in a cellular or personal communications network environment.
It is a further object 'of the invention to describe a speech recognition.system for use at a mobile telephone exchange (MTX) of a cellular or personal communications network. The placement of . . . . ,~ ...W, . , ~ ; .~. . . . . . .. . . 4 , ~: ; W A_'... .' , , ,.~.. _ ~ . ~. ,.: ,':' , . ,~ '. , WO 93/2 ~ 721 ~ ~ 1 ~ ~ ~ a PCT/US93/03491 ~x . ': w , _2_ the speech recognition system at the MTX
significantly reduces cost and increases reliability by enabling the switch vendor to install and maintain the system in conjunction with the cellular switch. .
It is another object of the invention to describe a cellular voice dialing system for use in or in conjunction with an MTX of a cellular network.
It is still another object of the invention to use voice recognition techniques to secure access to a cellular ar personal c~mmunications network.
Another object of the invention is to provide for combined use of speaker-dependent and spea~Cer-independent voice recognition and speaker Z5 verification techniques,in an MTX of a cellular or pexsonal communications telephone network.
These and other objects of~the invention are provided in an advanced system for the recognizing of spoken commands over the cellular telephone or any personal communications (i.e., any non-wireline) network. In the cellular application., for example, a Speech Recognition System interconnects either internally witY~ or as an eternal peripheral to a cellular telecommunicati~ns MTX switch. TYae Speech Recognition System includes an'~dministrative subsystem, a call processing subsystem; a speaker-dependent recognition subsystem, a speaker-independent recognition subsystem, and a data storage subsystem. The Speech Recognz,tion 3Q Sys em also allows for increased efficiency n the cellular teleQhone network by integrating with the , switch ~r switches as a shared resource. 7che administrative subsystem of the Speech Recognition , System is used to keep statistical logs of pertinent call information. Pre-recorded instructional messages are stored in the memory of the call '' ~ ~ W~ 93121721 ~ ~ ~' ~ ~ ~ '~ PCfiUS93103491 processing subsystem for instructing a user on his or her progress in using the system. The speaker-independent recognition subsystem allows the user to interact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem.
User specific attributes collected by the recognition subsystems are stored in the data storage subsg~stem.
The foregoing has outlined some of the more pertinent objects of the present invention. These objects should be construed to be merely illustrative of some of the more prominent features and applications of the invention. Many other beneficial results can be attained by applying the disclosed invention in a different manner or modifying the invention as will be described.
Accordingly, other objects and a fuller understanding of the invention may be had by re~erra,ng to the following Detailed I3escription of the~preferred embodiment.
For a more complete understand~.ng of the present inven- tion and the advantages thereof, reference should be made to the following Detailed Descr~.Qtion taken in connection with the accompanying drawings in which:
FIGURE 1 is a bl4ck diagram o~ a cellular telephone network incorporating an external switch-based Speech Recognition System according to the present invention;
FIGURE 2 i.s a block diagram of a cellular telephone network incorporating an internal switch-based Speech ReCOgnition System;
FTGURE 3 is an upper level block diagram of the Speech Recognition System and data storage subsystem of FIGURE 1;
~...: , '.''. . ..:: :-.. .:::: ,','~',..... .':'..~.. ~~:,'.;.' ;~.~. ..;.:: -.:':~:.. .~..',': ..' .':.. .:., y.'.... '.:..:.:.'.~~:.... ,., , . ".,:., ...... .:~.. . .. ,~....... , '... .~ ;.. . :..,, ..
. ' . .':.. .:. .'. '. ,,. ....'. ......:r. : ~.. ..:."..'. .': ~ . :...~ ; '.
, ...
'.' .,y ...
1 ' 'rv . ......" "..., ,...~ .. '~.~.: ,. , , .°... o .:w.:w ..~;':.
'~::,~ , ....,,.' :'.:'n ..:., .,.,T. .,.,:,... . ~.. . ,;.,.:... :..;.:,..',.
,....~_.
Vt~O 93/21721 ~ ~ ~ ~ ~ ~ PCT/1JS93/03491.~;
FIGURE 4 is a detailed component diagram of the speech recognizer beard of the Speech Recognition System of FIGURES 2 and 3;
FIGURE 5 is a flowchart showing a Control routine used in the Speech Recognition System;
FIGURE 6 is a flowchart of the Dial routine of the invention used'by the subscriber to voice dial a telephone number that has been previously-stared by the subscriber;
~.p FIGURE 7 is a flowchart of the Call routine used by the subscriber to voice dial a speaker-independent telephone number;
FIGURE 8 is a flowchart of the Directory Dialing routine used by the subscriber to recall a previously-stored number using a speaker-dependent directory name;:
FIGURE 9 is a flowchart of a Store routine used to st~re subscrfiber'--specific destination number information;
FIGURE 10 is a flowchart of a lYtemory routine used to store speed-dial numbers associated with specific memory locataons,~ and FIGURE 11 is a flowchart of a Directory Storage routine used to store speaker-depenc7ent directory names and associated telephone numlaers for use by the subscriber to seed-dial destination numbers based on the associated directory names.
Similar reference characters refer to similar parts or steps throughout the several drawings.
FIGURE 1 is a block diagram of a cellular telephone network incorporating an external , switch-based Speech Recognition System according to the present invention. Although the following , description is.specifically related to use of the Speech Recognition Sgstem a~ or in conjunction with an MTX of a cellular network, it should be r ~: ° ~: v.':: ,.,.,;... ,...,.,;. .:.:'.,. ..;.:.. ,.;:v.. , ~.:~;, ~
..,..,,,... ,..~~:, , ., ,,'~,-: ~~. . . ..... .;-..... ~':~..:.~~ ...;
.::'... .
.i-.1...;.. . :,'~.: ... ..,~n."., .'..': ,:, ~.~. ,... .. . _:., , . .......
.. ~,.~,. :., .,.. ,...... :. ....: ~... ..
~..~:.,...~.........."...... . .... ~..'.~..-. .. , i..,', .~.;~... ~
.,;~:.,.,.. ..:'..'::.... ..:.,' ,;','.......,... , ..,...:. . r.~, ~
...".,...,".,... ~... ..
fr f... .,..........,...".~.-....., ' .......~.. . ".:-..... .. ..;~~..,., , '.'..;,'.,.. ~ ~ " .._.~~.., ..., ~. . . . ....
,. , . . . . . ' .,:.:.; ~. .......a... ,..."_._ .. . . .. . . .
WO 93/21721 PCTIEJS93/03~91 _5_ appreciated that the System also interconnects either internally with or as an eternal peripheral to a personal communications network. Indeed, the principles of the invention are applicable to any cellular-like network application, i.e., where a non=wireline communications network is employed for mobile, sattelite. portable or personal communications. The Speech Recognition System can also be used as a shared resource through integration with a plurality of such non-wireline communications networks.
Ref erring now to FIGURE 1, an exemplary telephone network is a cellular network 10 having a mobile telephone exchange (MTX) switch 12 connected to a transceiver and are antenna 14. The transceiver is located in each cell of the cellular network and c~mmunicates with the MTX to effect transmission and reception of signals to and from the mobile tel~ghone located in vehicle 15. The transceiver is typically connected to the MTX via a leased or dedicated network line 12. The MTX 12 is typically connected ~o the land-based destinations via telephone network 16.
A cellular molbile telecommunications system connects'mobile telecommunications customers. each having a mobile unit, to land-based customers served by a telephone network. Incoming and outgoing calls are routed through a mobile telecommunications switching: office connected to a group of cell sites that-communicate with mobile knits. The mobile telecommunications switching office includes a mobile telephone switching exchange (MTX) for routing the calls between the mobi7.e units az~d the telephone network. In a typicallg mobile cellular communacations system, there are usually many cells per MTX and several MTX's per system. ~s used .. ~, f rt ~ , ...:. .:: ,~ ,.' s ..~ ~.. "~ . ... . .. . .. .....
.,..,,,::' . . -. ~ ~ ., ~~; ....~.; . .v :: ~,~ -: : . .........
' . ..._,!~... . ~:~.~' ., ,:.; s: . . . ,.,~'' ., . w::.. .. ~ ~.~~,~ ~__ wr.~~ .,.>:: v,: - ~, ,. ...,. -' -~" ~'." ...
VNO 93/21721 ~ ~ ~ ~ ~ ~ ~ PGTILJS93/034~3 y herein, "mobile telecommunications system'° refers to both cellular, sattelite and personal communications network environments.
Each cellular telephone is uniquely identified by two numbers: a serial number ('°ESN") encoded in y the phone by its manufacturer, and a mobile identification number ("MIN"), which is the cellular telephone number programmed in by the cellular service provider. The service provider operates the MTX 12 and keegs a database of all MIN°s (and their associated ESN's)': Each time a call is placed by the cellular telephone; the service provider verifies whether the MIN and the associated ESN are aufihori.zed. If the MIN and ESN of a cellular phone are not recognized (and the area code or NPA of the MIN indicates that the phone number is outside of the provider's ervice area), the provider normally allows the call'to proceed at least one time. If billing authorization cannot later be verified, however, the MIN and serial number are then glaced on an ezceQtion Iist. Subsequent attempts to use the MIN will then be rejected:
According to one embodiment of the invention as shown in F'IGtJRE l, a Speech Rec~gnition System 20 is connected as an external peripheral to the MTX
through a set of preferably digital trunk lines.
'Set 22 is used for incoming signals and set 24 is used for outgoing signals. Other types of signaling, such as CEPT E1 or analog, may also be used besides T1. The Speech Recognition System 20 is connected to a dedicated data storage subsystem , 26 through a data network 28. The data storage subsystem is used to store recognition data derived , from the subscribers to the voice dialing service as will be described. The Speech Recognition System 20 may be integrated with one or more switches (whether ' WO 93/21721 Pi.T/US93/03491 or not cellular for use as a shared resource via incoming and outgoing trunk sets 30 and 32.
Referring now to FIGURE 2, a block diagram shows the cellular telephone network 10' with the Speech Recognition System 20 interconnected internally to the MTX. This is the preferred embodiment of the invention: The hierarchical architecture of the cellular switch includes the central processing unit 33; memory 34, data storage disk 35; cellular interface 36, central office trunk interface 37 and a backplane or switching matrix 38.
The Speech Recognition System 2Q includes a number of functional subsystems: an administrative subsystem 21, a call processing subsystem 23, a speaker-dependent recognition subsystem 25, a speaker-independent recognition subsystem 27, and the data storage subsystem 29 (which corresponds to the storage system 26 of FIGURE 1). The administrative subsXstem 2~. of the Speech 20.Re~ognition System is used to keep statistical logs of pertu nent call information. Pre-recorded 'instructional messages are stored in the memory of the call processing'subsystem 23 for instructing a usex on his or her progress in using the system.
The~speaker-independent recognition subsystem 27 allows the user to intexact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem 25. User sgecific attributes collected b~ trie recognition subsystems are stored in the data storage subsystem ' 29:
F3GURE 3 is an''upper level block diagram of the Speech Recognition System,of FLGURE 1. The hierarchical architecture of the Sgstem 20 comprises a control central processing unit 40, a speech ,._..i .:' '..:~...,i, .., ~;. ,. ;..:.: ~ . ,.~... > ,.,',. ......'v.-:.
.'.,. .. ... . ....;,.. .' ..': ,.,_. . ' :, .. .
... . ,., v v: .,.. ,....... .. . ..
.'.~ ' .,': '~ '..;.,. . :" ,. .,.. ;. ,_.., . . :~. : . , ~~... .:: -' ':': .
.:,-:': . . : ... . " ~. :'. ., ... ..., .
.. . .. ,.. ..
~Cw.2f. .. ,'. .... .... ... . ~ :' . . ..' , " . ',~ . ..., . ~... . ' ' ..
": ' ~ . ...:.. ' . ......
.Yn.'. ,.,:~.. :'.'...~,:<:...,.... ..,_ ......:. o.,.
WO 33/21721 PGT/US93/03491 .< w'.
~l~.g~~~
recognizer board 41, a video drive circuit board 42, a disk drive controller board 43 with associated hard disk drive, telephone interface circuit boards ' 44~ and a local area network ('°LAN") interface board 45. A local area network 45 connects these ' components of the System to the data storage subsystem 29, which comprises a LAN interface board 47, a CPU contro~1 board 48 and a mass storage hard drive device 49. As also seen in FIGURE 3. a pulse code modulation ("PCM'°) highway connects the telephone interfacevboards 44 to the speech recognition board 41. The MTX is also connected to the System 20 through the interface boards 44.
The CPU 40 and associated control programs l5 function a~ the'system administrative subsystem 21 of FTGURE 2. The recognizer board 41 acts as the recognition call p~oc~ssing subsystem 23 and the redognition subsystems 25 and 27. Command and control functions are communicated t~ the recogni~er board 41 from the system administrative processor 40 to the recognition call processing subsystem through a System bus. Responses received by the administrative processor from the recognition subsystem a.ndicate primary and secondary recognition responses, error codes and command acknowledgements.
Referring now ~o FIGURE 4, a more detailed schematic diagram is sh~wn of the recogni~er board 41 of FIGURE 3 and modules 25 and 27 of FIGURE 2.
The recognizer includes a control digital:~signal processor ('°DSP'° ) 'S0 having an associated memory 51 for supporting control programs anc3 data. The control DSP 50 in this embodiment of the invention controls a-plurality of sgeech recognition digital signal processors 52a...52d via a control bus 53.
The control DSP 50 also connects ~o an interface processor 54 via a host port interface 55.
WO 93/21721 ~ ~ ~ ~ ~ ~ ~ . PCT/US93/03491 _g_ Interface processor 54 has its own processor memory 56. A buffer 57 interconnects the interface processor to a system bus interface circuit 58 that interconnects the recognizer board to the system bus.
The PCM highway of FIGURE 3 or backplane of FIGURE 2 is connected to a PCM highway interface circuit 59 that supplies speech sample information to the control DSP 50 and memory 51 via address and data bases 60 and 61. Each of the speech recognition DSP's 52a...52d has an associated memory 62a:..62d and storage buffer 63a...63d. Buffered 'address and data buses 64'and 65 interconnect to the address and data buses 60 and 61 through the buffers 66.
The'interface processor 64 converts batch system commands or command blocks received through the system bus-interface 58 into singular commands for the'control DSP 50. Similarly, singular responses from the control DSP 50 are buffered by the interface processor 54 and are sent to the administrative processor (of FIGURES 2 and 3) in code blocks to increase overall system efficiency.
The control DSP 50 performs an active hybrid funotion which allows the speech secognizer to recognize commands spoken by the user while outgoing messa,g~s are being played: A11 telephone channel signaling and PCM highway sample transfer is handled by the control DSP 50 through the PCM highway interface 59. The cootrol DSP 50 is also used to perform an active hybrid function as well as to send samples and commands ~o the four speech recognition DSP's 52a...52ri. The control DSP 50 advantageously extracts incoming speech information even while speech prompts'or messages are being played by the system. Additionally; the DSP's 52 can recognize words spoken by the user while such speech is being n.- s r t ~d.~.S.
!.. . . ' i.:~
. .a. .., :T .~.'f . .. .1 .
~. 1.
f W~a .
.s E.
. .I~.'. . .5~.:
ln:..
S
h .
,..n.;:
l '. ~ 1 . .e X F
t ...a 1 < 1~ .
v 5.
S T
..;>S: _. ~..a .r.l r .. 1. .
.s .,.
.~ ~t.
,"'L_.v r u'y'~':' ~! r:.k ;: .,.y ~,..
..1., ::
t ...
y. .
f ~,: 2 . . ~.. y ~w~
S..
k . ...4". , ....
x>,..
._.> ~ ,.'t. 1 . .. ., ifl.h.., . ,. ~ ~,~aF~, ....~',~.hS, . ... .t , ,...,.... .~ 4~v . ,... .
W!.7;, , VlrO 93I2I72~ PCTItJS93l03491 <~-r~~...
tr,,.. f -lo-played by the system. Additionally. the DSP°s 52 can function to stop outgoing messages based on detection of certain incoming speech energy.
The system data flow is such that recognition commands and responses are sent to and from the ' administrative processor and the speech recognition DSP°s 52 through the control DSP 50, the interface processor 54, and the system bus interface 58.
Speech samples are received by the speech recognition DSP's 52 through the PCM highway interface 59 and the control DSP 50.
The present invention facilitates the implementation of voice-dialing in a cellular telephone or other personal communications netwark environment. When a-user "subscribes" to the service (e.g.: with the MTX service provider), it is desirable that certain speech data be collected from the subscriber for security purposes. Thuso upon subscription, the user normally will be asked to provide his or her'native language (e. g.. English Spanish; French; etc.). a personal identification number, and personal information related specifically to the subscriber such as a social security number or date of birth. This latter information may be used in an automated query process ass wili be described to prevent fraudulent use of the cellular or personal telephone network.
Once the user information is activated in the system, the user may place or receive telephone calls. Initia~.l~, the user will be required to enter speed-dial numbers and their associated da. rectory names .
Referring -now to FIGURE 5, a functional flowchart is provided describing the basic control functions of the Speech Recognition System according to the present invention. The routine begins at W~ 93/21721 ~ ~ ~ ~ ~ ~ '~ PC'f/ZJS93/03491 step 102 when the user dials digits from the cellular telephone. At step 104, a test is performed to determine if a Speech Recognition System access code has been dialed. Tf not, the cellular switch processes the call based on the number dialed at step 106 and the routine ends. If the result of the test at step 104 is positive, the routine continues at step 108 during which the switch makes an audio path connection between the user and the Speech Recognition System. At step 110, the switch sends the user's mobile identification number ("MIN") to the Speech Recognition System. As noted above. the M7:N is a unique number associated with a given cellular telephone that is available to the switch each time a telephone call is placed.
According to the invention, each user who subscribes to the service will have prerecorded a List of destina~zon numbers: At step 7.10. these speed-dial numbers, along with speaker-dependent emplates an:d user language type data, ,are retrieved from the data storage subsystem. As noted above, the data' torage subsystem stores such data at predetermined locations that are preferably accessed by the MIN: The routine then continues at step 17:2 with the Speech Recognition System prompting the user thatit is "Ready,For Command" or the like. The command is made in the language as determined by the user language type data retrieved at step 110. At step 114; the Speech Recognition Systems engages the speaker-independent recognition subsystem to obtain the user response. Depending on the response, one o'f several different subroutines follow.
If the user states and the system recognizes a "Dial" command, control is passed to the Dial ,~ v , ' :.~~. . . , ~ ~ ' ~ ,:~' -. :. ...,. ,.. , .,.. ~:.
s ~S ~.:- "~~.i . . ,. , , ~.,. .. ,... ..~ -.. ,. ,.., . . ,. .. .,., . .
WO 93121721 PGT/US93/03491 , ~ :~ ~. 8 ~. 3 ~ -12-Routine of FIGURE 6. In particular, a test is made at step 116 to determine if the Dial command is recognized. If so. control is transferred to the ' routine of FTGURE 6. If the response to the test at step I16 is negative, a test is made at step I18 to ' determine if a °'Call" connmand has been spoken and recognized. If the system recognizes a "Call"
Command. control is passed to the Call Routine of FIGURE 7. If 'the response to the test at step 118 ~.s negative, a test is made at step 120 to determine if a "Directory" command has been spoken and recognized. If the system recognizes a "Directory"
Command, control i~ passed to the Directory Dialing Routine of FIGURE 8.
~f the result of the test at step 120 is negative, a test is made at step 122 to determine if the user has spoken a ",Quit" command. If so, the routine terminates. If the result of the test at step I22 ~.s negative, the Speech Recognition System responds with a error message in step 124. A test is then performed at step 126 to determine if a predetermined maximum error count has been reached.
Tf not, control is transferred back to step 114. If the predetermined maxianum error count has been reached, the call and the MIN is transferred to an opexator at step 128 and the routine ends.
Referring now to FIGURE 6, the Dial Routine is described in detail. At step 130. the Speech Recognition System prompts the user with a message, such as "Phone Number Please," and applies the speaker-independent recognizer to collect the digits. A test is performed at step 132 to determine whether a digit has been collected. If not, a test is made at step 134 to determine if a predeterm~.ned timeout has elapsed. A negative response to the timeout step returns control back to x y t V us :. ~ s . .; ~~
~r ..,?.. ,. .., ,., . ~ '..~~ , . L.,.n . ,. xay . .., ,.... ,.
. z _13_ step 132. If the outcome of the test at step 134 is positive, the routine performs a test at step I36 to determine if at least the first digit of the phone number to be called has been entered. If so.
another test is performed at step 138 to determine if a maximum error count has been reached. If the outcome of the test at step 138 is negative, the Speech Recognition System promgts the user to "please enter nest digit"'at step 140 and control :returns-to step I32:
If, however, the outcome of the test at step 136 is negatives the routine tests to determine whether a maximum error count has been reached at step 142. If not. control returns to step 130 to request the user to enter the,phone number. If the outcome of the test at either step I38 or 142 is positive, the call (with the MIN) is transferred to an ogerator at step 144 and the routine ends.
If the outcome'of the test at steg 132 is positive, the recognizes preferably responds with a short beep'or other.audible indication at step 146.
.A test is then made at step 148 to determine if the digit collected'is the last digit expected in the string. If not:, the digit is saved'in a-string buffer at step 149 and the routine returns to step 132 to collect''another digi . If, however, the oui~come of step 148: is positive: all digits have been collected and he speaker-independent recognition subsystem is engaged at step 150.
At step 152, the subsystem attempts to verify the called number. If the verified ion command is not recognized, the Speech Recogniirion System responds at step 154 with a message such as "Error, Please repeat," and control returns back to step 152. If the outcome of the test at step 152 is positive, the telephone number is repeated to the ... . . ... . , .,... , . ,..,. . . . , ., . ..,." .a..,:... ~. .
WO 93/21721 ~'CflLJS93103491 ~"'~, user at step 156 and the speaker-independent recognition subsystem is engaged.
A test is then made at step 158 to determine ' whether the user (by spoken command) desires to "Store'° the number. If yes, the control is ' transferred to the Store routine of FIGURE 9. If the outcome of the test at step 158 is negative, a test 162 is made to determine whether the user has spoken (and the recogni~er has recognixed) a "Send"
~.0 command: If not, the Speech Recognition System again plays an error message at step 164 and control ~,s returned to step 158. A positive response to the "Send" test made at step 162 transfers the MIN and the string dialed to the switch for outdialing.
Such transfer occurs at step 166. At step 168, the switch dials the telephone number and connects the user to the dialed nbmber.
The Call routine is shown in detail in FIGURE
7: The routine begins at step 170 during which the Speeclh Recognition System responds to the user's "Call"' command with a message "Calling." At step 172, the speaker independent recognition subsystem is engaged to obtain the user°s response. A .test is then made at step ,174 to determine if the user spe~k~ a "Memory.' command; indicating that the number to be called is to be stored and made available for speed--dialing once a preferably two digit memory i~cation number is subsequently received. If the outcome of the test at step 174 is positive, the Speech,Recognition System queries the user °'Which memory" and engages the'recognition subsystem at step'176. At step 178: a test is made ~a determine if a two digit memory location has been identified by the user. If a two digit memory location-has not been'identified, a timeout test is performed at step 180. If timeout occurs, the ,: . ::: . .: . ," ..: ... ,... . .,,. ,; . .. . . . ..;, .
_ _ . ..
. : . : .... ~ -:. .. .~. ~ _ -; , : .... . . ; :.: . . : ,;;,.
r . .,. . .: .:~: : . . -::. ... v::: ,:.., .. .. . ,; ,, ~:: .; :,: ,~.,;e:
... ... ; .: -:.,. . ':. :. ., ,. . ,. .. ,._: " ... ..:. ..:: .. : :...:..., . ;: . .: , :. , . ,. . . ., ... .::'; ... ~ . ....
:."
~;,::~:: r:;:. ..:.~..:r.~,., : ~.:~..; .... ~.. .-.~. .,:. ,..."~. .:,....
..,.... .:.............:. ....,. . '~......,...... ~..::w.;..: ......:. ~..
..:>..:w..:,,...,." .,........ ...,..
5' ~, ;'. . .. . . , C, 'riv~ .. . . . ~.., ~ ... . . ..
':-,._- .. .. :.: r: ~. .~., .. . ... . - . . , ......, . . .... .
f..<~~.~:;.~, WO 93f21729 PCf/US93103491 Speech Recognition System prompts the user to °°Please enter newt digit" at step 182 and control is returned to step 178. A negative outcome of the timeout test also returns control back to step 178.
A posative outcome of the test at step 178 indicates that the two digit memory code has been received: The routine then recalls the previously-stored telephone number associated with the memory code at, step 184. The Speech Recognition System then notifies issues a "Calling" message to the user,at step X86.
A user may also retrieve the stored telephone number by speaking one of the speaker-independent key words. Thus, if the outcome of the test at step 174 is negative, the routine continues at step 187 with the user speaking a valid key word associated with one or more previously-stored telephone numbers. Without limitation, such key words include HOME, OFFICE, TI1KE, ' SECRETARY, FRIEND, ~rIORK and rINFORMATION. A test is then made at step 188 to determine if the work spoken is a valid key word.
If not: the system xesgonds with an error message at steps 190 and asks the user to speak the word again at steQ 1~7. A gositive outcome to the test at step 188 transfers control to step 186.
At step 192, the speaker-indepe~adent subsystem is again engaged to obtain a user command. A test is made at step 194 to determine whether the user desires to "Verify" the number retrieved. If a 3a "Verify" command is spoken and recognized, the s~bred number associated with the key word is repeated to the user and the recognizer is engaged at step I96. A test is then made at step 198 to determine whether he user desires to "Clear" the number retrie~red and start again: If so, the Speech ~~t'>.,::,.. .. ...': ,~, , .,. ~..,..,'. . . ~ ., .,., "... .,.. .'': . . .
WO 93/ZI721 FGT/US93/03491;.«'"
~I~~~~~ --16-Recognition System responds with a "Ready" message at step 200 and control returns to step 187.
If, however, the ~utcome of the test at either ' step 194 or step 198 is negative, a test is made at step 202 to determine if a "Send" command has been ,' spoken and recognized. If not, the system responds with an error message at step 204 and returns to step 192. If the user speaks the "Send" message, the Speech Recognition System responds at step 206 with a "Dialing" message. At step 208. the System transfers the MIN and the telephone number to be dialed to the Switch for outdialing. The switch dials the telephone number ana connects the user to the dialed number at step 210.
1S Referring now to FIGURE 8, a flowchart is shown of the Directory Dialing routine. This routine is called'when the user desires to recall and dial some previously-stored telephone numbers using a previously~stored speaker-dependent name. In response to'the "Dir.ectory" command from the user, the routine plays a message at step 212 to request the name in the directory. Step 212 also engages :the speaker-dependent recognition subsystem. A test is then made at step 214 to-determine if the name has been collected from the speaker. If no response is obtained. a timeout test is performed at step 2L6. Failure of the speaker to respond before the end of the timeout causes the issuance of an error message at step 218,and the routine.returns to step , 214. If the timeout occurs without the speaker's respanse, control is transferred back to step 212.
A positive outcome of the test' at s e~ 214 means that the directory name spoken by the user has been recognized. The routine then continues at step and recalls from the data storage subsystem a number associated with such name: At step 222, the S P
. , ,...':.1 ,.. ~'. ';. ~;. ~. ~ ;) .,~ ... . . . ~ ,. ~ . ..... ,....
a '...!' ..: S .. ..
i . 1 ..
r~:.:
..Vt .-: \ -a: 1..., .. ......,~.St~~ .. . . , .. ;..~~ ......... ,... >.x . ." ,.., ...,.... _ ..,.... ,. , C,ty...n...., . . .....,. , . ... ..
W~ 93/21721 , ~ ~ ~ ~ ~ ~ '~ PCf/Z.JS93103d91 -:. .:: ,;
stored number is played to the user and the Speech Recognition System issues a "Correct" prompt. A
test is then made at step 224 to determine if the number is correct. If not, control is returned back to step 212. If the outcome of the test at step 224 is positive. then the Speech Recognition System ' responds with a ''Dialing" message at step 226. At step 228, the System transfers the MIN and the telephone number to be dialed to the switch for outdialing. The switch dials the telephone number and connects the user to the dialed number at steg 230.
Referring now to the Store routine FIGURE 9, a flowchart is shown of a routine used by the 15' subscriber to store telephone numbers for the two digit memory codes, keywords, and directory names to be later dialed. The routine begins in response to receipt of a speaker'-independent ''Store" command spoken by the user to update the speed-dial list whenever necessary. At step 232, the routine responds to the command with a "Storing°' message and engages the speaker-indegendent recognition suk~system. A test is then made at step 234 to determine whether the user desires to store twa digit memory codes. If so, control is transferred to the Memory routine of FIGURE 10. If the outcome ofthe test at step 234 is negative, a test is made at step 236 to determine whether the user desires to store a Directory name or a number associated with a Directory name. If so, control is transferred to the Directory Storage routine of FIGURE 11. If the outcome of the test at step 236 is negative, then the system will'expect to receive a key word for association with the number to be stored at step 238. A test is thus made at step 240 to determine whether the subscriber has spoken a valid key word.
~' v »'a ~.., '.°.-:. . .. C4 y . , . . . .. ..,. .. ....... .. . . .,- .. .
...r..
W~ 93/21721 ~ . ~ PCT/US93/m3491 ~1~~~3~
If not, the system responds with an error message at step 242 and control is returned to step 234. Tf the outcome of the test at step 240 is positive, the ' Speech Recognition System makes an inquiry "Storing (key word), correct" and engages the ' speaker-independent recognition subsystem at step 244. A test is then made at step 246 to determine if the user selection is correct. If not, the Speech Recognition System issues a "Location, please" prompt at step 248 and returns to steg 240.
A positive outcome of the test at step 246 causes the system to issue a "Storing" prompt while a number associates with the keyword is stored in the data storage subsystem in step 249. Control is then returned to step 112 in FIGURE 5.
The Memory routine is shown in FIGURE 10. The routine begins at step 2~0 by inquiring '°'Which memory" and'engages the speaker-independent recognition subsystem. At step 252, a test is made to determine if a two digit memory location number has been collec ed from the user. A timeout test is then performed at step'254. If timeout occurs, the Speech Recognition System prompts the user to "Please enter~nezt digit" at step 256 and control is returned to step 252. A negative outcome of the timeout test also returns control back to step 252.
A positive outcome of the test at step 252 indicates that the two digit memory code has been collected from the subscriber. At step 258, the Speech Recognition System responds with a message "Storing memory (2 digits), correct" and emgages the speaker-independent recognition subsystem. A test is then made at step 260 to confirm that the subscriber is storing the telephone number in the appropriate location. If not, the Speech Recognition System issues a "Location, please"
,., ...6°...': .';; s .,. " ,-; ..-. ..-.....
.~:v:~:;:°:,:;:~, , ..:....,... ,,.. ., .... . .. :.y. . ~...,.:~.~,.
...~:.:':. ~. ~. .~:. :: ..:,!~ ,.., ~.., .... ~.~.~.,;.. ... ~ ..n.~.~:::~.
,:~.....a::.~...:...'. . ..
'.'.,°,' .:iw°, . .. ....,..
r.,.: ~ r;:~ . ...';;5. ...,. ~ . ......
. , .1..... . . .. , .,. .. ... . ., .. . .....
s,;...,., w0 93/21721 PCT/US93/~3191 _lg_ prompt at step 262 and returns to step 252. A
positive outcome of the test at step 260 then causes the routine to test at step 264 whether the memory is already filled up with stored codes. If not,..the system issues a "Storing" message and stores the number in the data storage subsystem at step 265.
If, however, the response to the test at step 264 is affirmative, the Speech Recognition System issues a "Memory full, erase?" message and engages the speaker-independent recognition subsystem at step 266: A testis then performed at step 268 to c7etermine whether the speaker wishes to erase a memory location: If not, control returns to step 112 in FIGUR& 5. , 1~ If the subscriber desires to erase a given memory location code, the system issues a "Confirm ~r,~se'i message at step 270 and engages the speaker-independent recognizer. An erase test is then gerformed again at step 272 to confirm that the 'subscriber wishes to.erase the specified memory location. A negative outcome of the test at stag 272 returns cohtrol to step I12 in FIGURE 5. A
positive outcome of the erase test at step 272 causes the system o issue an acknowledgment at step 274: Control then returns to step 112 in FIGURE 5.
Referring-now to FIGURE 11; a flowchart is shown of the Direct~ry Storage routine. The routine begins at step 276 in response to a positive response to the Directory inquiry performed in step 236 in FIGURE 9 (i.e:, receipt of the Directory dommand): Step 276 issues a prompt to the subscriber to determine if a "Number in Memory" has been previously associated with a Directory name. A
test is then performed at step 278 to determine if the Number in memory has been previously stored. If not, the Speech Recognition System responds by WU 93/21721 ~ ~ ~ PC~'/US93/03491 ~~ ~.~~. i~ -20-issuing an "Enroll" message and engages the speaker-independent recognition subsystem at step 280. A test is then made at step 282 to determine whether the subscriber wishes to enroll. If not, the routine terminates and returns to step 112 in f'IGURE 5.
If the outcome of the test at step 278 is affirmative, the Speech Recognition System issues a message "Re-enroll" and-engages the l0 speaker-independent recognition subsystem at step 284. A test is then made at step 286 to determine whether the subscriber wishes to re-enroll the directory name. If yes, or if the outcome of the test at step 282 is positive, the routine continues a~ step X88 and issues a HName Please" message and engages the speaker=dependent recognition subsys em. The user then speaks the name a predetermined numbex (e: g., three (3) times) at step 290 to program the speaker-dependent subsystem. The new directory name and the associated telephone ,number are then'stored in the data storage subsystem in step 292. Control is then returned to step 112 in FIGURE 5:
If the outcome of the test at step 286 is negative;'the Speech Recognition System issues a message "Erase°' and engages the speaker--independent recognition subsystem at step 296. A test is then made at step 298 to determine whether the subscriber wishes to erase the directory number. If so, the associated number is erased at step 300. Control is thea~ returned to step 112 in FIGURE 5.
It should be appreciated that tk~e specifis names of the commands are merely exemplary and .
should not be taken by way of limitation. Other suitable command ra~mes are of course suitable.
. ..:: . .~:~ . . ....:... .. ;. a . . . .: . ... . :~ : , ; :: ''';.:: :. ' ':~.,.. :.:; .;.:.
t~.x~ . . . . . :. ; , .. . .. , ........ ... .. .,... , .
dV0 93/23721 ~ ~ ~ ~ ~ PCT/US93l03491 _21_ As noted above, each cellular telephone is uniquely identified with its MIN and ESN. In the prior art, the service provider operates the MTX 12 and keegs a database of all MIN's (and their associated ESN's): Each time a call is placed by the cellular telephone, the service provider verifies whether the MIN and the associated ESN are authorized: If the MIN ana ESN of a cellular phone are not recognized in the switch database, the provider normally allows the call to proceed at least one time, If billing authorization cannot later be verified, however, the MIN and serial number are then placed on an exception list.
Subsequent attempts to use the MIN will then be 1.5 rej acted .
Such fraudulent use of the cellular network is ameliorated by the present invention. According to another feature of the invention, the Speech Recognition System also includes a positive idbntification function that enables the system under certain circumstances to test whether the user ~assaciated vrith a received MIN (whether in or out of the service area) is an authorized subscriber to the service. For ~egamgle; after a call is voice-dialed and the Send command is spoken, the system might prompt the caller to answer one or more personal quest~.ons. Thus, the caller might be requested to speak the social security and%or account number of the-subscriber (purportedly associated with the MIN
and ESN). Alternatively, the caller can be prompted ~o enter such identifying information manually through the telephone keypad. Of course. the nature and scope of the personal information requested by the system depends entirely on the system operator 3~ and the degree of security sought by the subscriber and operator.
V6~~ 93/21721 PC'TIUS93/03491': '"
~~~~8~_3~
Such a system could also be used to prevent a local call being placed from a stolen vehicle, for example, i.e., even if the MIN was recognized in the service provider's database. It could also be used to limit access to the voice-dialing function from ' the subscriber's phone to certain persons. Thus the subscriber may limit his or her children or others from using the phone without the subscriber's knowledge. If the user cannot provide proper answers to such questions, he system rejects the SEND command and the call is terminated. Correct entry of the requested information enables the caller to continue hi or her access to the service.
Alternatively the identification function may be implemented in conjunction with a speaker verification function in which the user's identity must first be verified with some spoken predetermined personal identification code. If the verification function is not 'convinced" that the person is wha he or she claims to be, the identification function is then executed to ask the follow-up questions. One such system is described in copending ~pPlication Serial No. 07/523,486, filed May 15, 1990. to Hunt et al, titled "Simultaneous Speaker-Independent ~'c~ice Recognition And Verification Over A Telephone Network,' assigned to the assignee of'the present invention.
The present invention had numerous advantages over the prior art. The system combines the use of bo1~h speaker-dependent'and speaker-independent speech recognition in an mobile or portable telephone communications network environment.
Multiple language prompts are spoken'from and available simultaneously on.multigle ports from a single automated telecommunication -based system.
The language selected is based on the language ~ - :. : , : y::., - : ,: . :.
c , ,, , ;:, : , . . ~ =. . ': : v'' . . : . .
,:
F.. ~
. ~c.. .. '. v ..
.v v .,..." r . . ." 4.,. , ,. :;,. , ., - , ": :: , v : ; ,. : ; .. :, w ' ;.:,.:
. '..
3 . 7 .. ). ..
.,., ~ ....,...,.a:.,....... t.. ~ .:. '..':: ..., .. ..
i ',...:. . . .. : : ... . ~ :: , : : . ~ : ~ ..,: . :, . ::: ~ ,~: :' a ..,...:: . . r .;....., ,.a .: _. ,~. .. . ..:.. ~.. . ~: .. ~ . :.' ~ . . , '., '. :~ ' :.. .. ,. , ~'u , . a~..:., ,:.:,.<~:~:.; .i~.'..!f. ., '~,.'~: .. ,.v::i.~.! ....., ~:. .
....,.. .:',.'~':. ,~..w,w, ~.,.',~~..,.. .n ..:..:.:' .. '..~. ~ ..... ...,.
..., . . .. . ..
WO 93/21721 ~ ~ ~ ~ ~ ~' ~ PCTlUS93/Q3491 ,. -23-spoken by the user. The system advantageously stores user specific speaker-dependent and speaker-independent speech information with particular user-based addresses.
The invention successfully implements speech recognition in the cellular telephone or personal communications network. Non-wireline networks provide a special challenge to both the recognition algorithm developers as well as the applications developers. The recognition algorithm in conjunction with the system application is insensitive to the radio fading, speech clipping, and speech compression conditions that occur in a non-wireline network: In addition, the recognition 1.5 algorithm accommodates conditions found in the standard-switched network. The invention provides a means ~f accurately recognizing speech that has l~,m;ited distortion'' due to clipping or fading and provides a means of reprompting the user for input when the speech has become too distorted for accurate recognition.
Previously, onlg the best examples of spoken words have been used as tokens for developing speech vocabularies. ~y collecting speech that has been compressed or that although distorted by radio fading or clipping is still intelligible and by adding this collected speech to the speech training database the vocabulary based on such data becomes more robust and Iess sensitive to these conditions.
Adding the distorted but intelligible data to the training database'of excellent example words allows for a more diverse statistical representation of each vocabulary word. Words that might have been previously rejected: because part of the word was clipped can now be recognized if enough intelligible information is available. If the statistical dV0 93/21721 PCT/US93/03491 :'"
:z:
~~~.~~3~
representation of the word indicates that not enough information is available for accurate recognition, the recognition system will reject the word and ' reprompt the user for input.
The invention also enables real-time vocabulary uploading. Previously, speech recognition vocabularies were stored in memory and were not updated or totally changed during the operation of an application: The present invention solves the lp problem of allozaing speech recognition vocabularies to be loaded into a recognition system while an application is in operation. This capability allows for less high speed memory to be used in a system, because an entire set of vocabularies is not required to be resident in memory at one time. This capability also allows for efficient memory management zahen multiple languages are used, because onllr the language required by the system user need be resident in memory at any one time. Previously, zp all possible languages required by users would have been stored in memory simultaneously.
Both continuous and discrete recognition techniques ire used in the Speech Recognition. System of the present invention.
It shQUld be appreciated by those skilled in the ark that the specific embodiments disclosed above may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present invention. It should also be realized by those skilled in the art that such equivalent constructions do not depart from the spirit anc3 scope of the invention as set forth in the appea~ded Claims:
Claims (11)
1. In a mobile telecommunications system that connects mobile telecommunications customers, each having a mobile unit, to lend-based customers served by a telephone network, wherein incoming and outgoing calls are routed through a mobile telecommunications switching office connected to a group of cell sites that communicate with the mobile units, the improvement comprising a voice recognition system located at the mobile telecommunications switching office, the voice recognition system comprising:
a voice recognizer for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a first. spoken command from said mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of said program and responsive to receipt by the voice recognizer of a second spoken command from the mobile unit customer, for transferring the identifying information received by the voice recognizer to the mobile telecommunications switching office.
a voice recognizer for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a first. spoken command from said mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of said program and responsive to receipt by the voice recognizer of a second spoken command from the mobile unit customer, for transferring the identifying information received by the voice recognizer to the mobile telecommunications switching office.
2. The mobile telecommunications system as described in Claim 1 wherein the voice recognizer includes means for verifying the mobile unit customer's identity.
3. The mobile telecommunications system as described in Claim 1 wherein the identifying information comprises one or more digits of the destination number.
4. The mobile telecommunications system as described in Claim 1 wherein the identifying information comprises a keyword associated with the destination number.
5. The mobile telecommunications system as described in Claim 1 wherein the identifying information comprises a code associated with the destination number.
6. The mobile telecommunications system as described in Claim 1 wherein the processor means is further operative under the control of the program and responsive to receipt by the voice recognizer of a third spoken command from t:he mobile unit customer, for controlling the announcing means to announce the identifying information received by the voice recognizer to enable the mobile unit customer to verify the information prior to issuing the second spoken command.
7. The mobile telecommunications system as described in Claim 6 wherein the first spoken command is Dial, the second spoken command is Send and the third spoken command is Verify.
8. In a mobile telecommunications system that connects mobile telecommunications customers, each having a mobile unit, to lend-based customers served by a telephone network, wherein incoming and outgoing calls are routed through a mobile telecommunications switching office connected to a group of cell sites that communicate with the mobile units, the improvement comprising a voice recognition system located at the mobile telecommunications switching office, the voice recognition system comprising:
a voice recognizer for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a first spoken command from the mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of the program and responsive to receipt by the voice recognizer of a second spoken command from the mobile unit customer, for controlling the announcing means to announce the identifying information received by the voice recognizer to enable the mobile unit customer to verify the information;
the processor means also operative under the control of the program and responsive to receipt by the voice recognizer of a third spoken command from the mobile unit customer, for storing the identifying information received by the voice recognizer for subsequent retrieval and use by the mobile unit customer.
a voice recognizer for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a first spoken command from the mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of the program and responsive to receipt by the voice recognizer of a second spoken command from the mobile unit customer, for controlling the announcing means to announce the identifying information received by the voice recognizer to enable the mobile unit customer to verify the information;
the processor means also operative under the control of the program and responsive to receipt by the voice recognizer of a third spoken command from the mobile unit customer, for storing the identifying information received by the voice recognizer for subsequent retrieval and use by the mobile unit customer.
9. The mobile telecommunications system as described in Claim 8 wherein the first spoken command is Dial, the second spoken command is Verify and the third spoken command is Store.
10. A mobile telecommunications switching office connected between a telephone network and a group of cell sites that communicate with mobile units, comprising:
a mobile telephone switching exchange for routing incoming and outgoing calls between the mobile units and land-based customers served by the telephone network;
a voice recognizer for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a first spoken command from the mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of said program and responsive to receipt by the voice recognizer of a second spoken command from the mobile unit customer, for transferring the identifying information received by the voice recognizer to the mobile telecommunications switching office.
a mobile telephone switching exchange for routing incoming and outgoing calls between the mobile units and land-based customers served by the telephone network;
a voice recognizer for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a first spoken command from the mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of said program and responsive to receipt by the voice recognizer of a second spoken command from the mobile unit customer, for transferring the identifying information received by the voice recognizer to the mobile telecommunications switching office.
11. A voice recognition system for use in a mobile telecommunications switching office connected between a telephone network and a group of cell sites that communicate with mobile units, the mobile telecommunications switching office including a mobile telephone switching exchange for routing incoming and outgoing calls between the mobile units and land-based customers served by the telephone network, comprising:
a voice recognizes for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizes of a, first spoken command from the mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of said program and responsive to receipt by the voice recognizes of a second spoken command from the mobile unit customer, for transferring the identifying information received by the voice recognizes to the mobile telecommunications switching office.
a voice recognizes for recognizing characters and commands spoken by a mobile unit customer;
announcing means; and processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizes of a, first spoken command from the mobile unit customer, for controlling the announcing means to request the mobile unit customer to enter information identifying a destination number to be dialed;
the processor means further operative under the control of said program and responsive to receipt by the voice recognizes of a second spoken command from the mobile unit customer, for transferring the identifying information received by the voice recognizes to the mobile telecommunications switching office.
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US867,873 | 1992-04-13 | ||
US07/867,873 US5297183A (en) | 1992-04-13 | 1992-04-13 | Speech recognition system for electronic switches in a cellular telephone or personal communication network |
PCT/US1993/003491 WO1993021721A1 (en) | 1992-04-13 | 1993-04-13 | Speech recognition system for electronic switches in a cellular telephone or personal communications network |
Publications (2)
Publication Number | Publication Date |
---|---|
CA2118135A1 CA2118135A1 (en) | 1993-10-28 |
CA2118135C true CA2118135C (en) | 2000-06-13 |
Family
ID=25350638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CA002118135A Expired - Fee Related CA2118135C (en) | 1992-04-13 | 1993-04-13 | Speech recognition system for electronic switches in a cellular telephone or personal communications network |
Country Status (8)
Country | Link |
---|---|
US (6) | US5297183A (en) |
EP (1) | EP0636294B1 (en) |
AT (1) | ATE198688T1 (en) |
AU (1) | AU672202B2 (en) |
CA (1) | CA2118135C (en) |
DE (1) | DE69329850T2 (en) |
ES (1) | ES2156871T3 (en) |
WO (1) | WO1993021721A1 (en) |
Families Citing this family (216)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2264209B (en) * | 1992-02-06 | 1995-11-08 | Technophone Ltd | Cordless telephone arrangement |
US5297183A (en) * | 1992-04-13 | 1994-03-22 | Vcs Industries, Inc. | Speech recognition system for electronic switches in a cellular telephone or personal communication network |
US5717743A (en) * | 1992-12-16 | 1998-02-10 | Texas Instruments Incorporated | Transparent telephone access system using voice authorization |
US5717738A (en) * | 1993-01-11 | 1998-02-10 | Texas Instruments Incorporated | Method and device for generating user defined spoken speed dial directories |
US5566272A (en) * | 1993-10-27 | 1996-10-15 | Lucent Technologies Inc. | Automatic speech recognition (ASR) processing using confidence measures |
SE9304222L (en) * | 1993-12-21 | 1995-06-22 | Telia Ab | Method and device for calls from mobile stations |
US6081782A (en) * | 1993-12-29 | 2000-06-27 | Lucent Technologies Inc. | Voice command control and verification system |
US5524169A (en) * | 1993-12-30 | 1996-06-04 | International Business Machines Incorporated | Method and system for location-specific speech recognition |
DE4401518A1 (en) * | 1994-01-20 | 1995-07-27 | Telefonbau & Normalzeit Gmbh | Method for operating an automatic ordering system in communication switching systems |
WO1995025649A1 (en) * | 1994-03-18 | 1995-09-28 | VOICE CONTROL SYSTEMS, INC. formerly known as VCS INDUSTRIES, INC., doing business as VOICE CONTROL SYSTEMS | Speech controlled vehicle alarm system |
US6996542B1 (en) * | 1994-06-03 | 2006-02-07 | Midwest Payment Systems | System and method for paying bills and other obligations including selective payor and payee controls |
US5586171A (en) * | 1994-07-07 | 1996-12-17 | Bell Atlantic Network Services, Inc. | Selection of a voice recognition data base responsive to video data |
US20040113794A1 (en) * | 1994-10-27 | 2004-06-17 | Dan Schlager | Self-locating personal alarm system equipped parachute |
US5509049A (en) * | 1994-10-31 | 1996-04-16 | Voicetech Communications, Inc. | Automatic dialing of number received from directory assistance from within cellular system |
NZ294659A (en) * | 1994-11-01 | 1999-01-28 | British Telecomm | Method of and apparatus for generating a vocabulary from an input speech signal |
WO1996018258A2 (en) * | 1994-12-02 | 1996-06-13 | Voice Control Systems, Inc. | Intelligent call processing platform for home telephone system |
US5680506A (en) * | 1994-12-29 | 1997-10-21 | Lucent Technologies Inc. | Apparatus and method for speech signal analysis |
US5724481A (en) * | 1995-03-30 | 1998-03-03 | Lucent Technologies Inc. | Method for automatic speech recognition of arbitrary spoken words |
US5822727A (en) * | 1995-03-30 | 1998-10-13 | At&T Corp | Method for automatic speech recognition in telephony |
US6459910B1 (en) * | 1995-06-07 | 2002-10-01 | Texas Instruments Incorporated | Use of speech recognition in pager and mobile telephone applications |
DE19521901A1 (en) * | 1995-06-16 | 1996-12-19 | Sel Alcatel Ag | Communication system with speech controlled activation of services |
JP3968133B2 (en) * | 1995-06-22 | 2007-08-29 | セイコーエプソン株式会社 | Speech recognition dialogue processing method and speech recognition dialogue apparatus |
US5784456A (en) * | 1995-06-29 | 1998-07-21 | Cyracom International, Inc. | Single-line multi-handset telephone |
US5651056A (en) * | 1995-07-13 | 1997-07-22 | Eting; Leon | Apparatus and methods for conveying telephone numbers and other information via communication devices |
EP0758187B1 (en) * | 1995-08-09 | 2005-05-11 | Hewlett-Packard Company, A Delaware Corporation | Radio base station for a private telecommunications system |
AU7007796A (en) | 1995-08-15 | 1997-03-12 | Amsc Subsidiary Corporation | Improved mobile earth terminal |
US5815809A (en) * | 1996-04-16 | 1998-09-29 | Amsc Subsidiary Corporation | Mobile earth terminal communication device providing voice, data, facsimile, and/or roaming communication features |
KR0144388B1 (en) * | 1995-08-24 | 1998-08-01 | 김광호 | Multi-language display method |
DE19533541C1 (en) * | 1995-09-11 | 1997-03-27 | Daimler Benz Aerospace Ag | Method for the automatic control of one or more devices by voice commands or by voice dialog in real time and device for executing the method |
JPH09114489A (en) * | 1995-10-16 | 1997-05-02 | Sony Corp | Device and method for speech recognition, device and method for navigation, and automobile |
US5771452A (en) * | 1995-10-25 | 1998-06-23 | Northern Telecom Limited | System and method for providing cellular communication services using a transcoder |
US6078804A (en) * | 1995-12-19 | 2000-06-20 | Ericsson Inc. | Providing different routing treatments for emergency calls based on subscriber specified data |
US5684869A (en) * | 1995-12-27 | 1997-11-04 | Lucent Technologies, Inc. | Telephone station remote access device and method |
US6081583A (en) * | 1995-12-27 | 2000-06-27 | Lucent Technologies Inc. | Post call directory entry device and method |
US6073101A (en) * | 1996-02-02 | 2000-06-06 | International Business Machines Corporation | Text independent speaker recognition for transparent command ambiguity resolution and continuous access control |
US6198947B1 (en) * | 1996-02-28 | 2001-03-06 | Oki Telecom, Inc. | External control unit with reduced keypad integrated in voice activated vehicular telephone system with call-in-process voice-to-tones and voice to-memory conversion facilities |
US5719921A (en) * | 1996-02-29 | 1998-02-17 | Nynex Science & Technology | Methods and apparatus for activating telephone services in response to speech |
US5905773A (en) * | 1996-03-28 | 1999-05-18 | Northern Telecom Limited | Apparatus and method for reducing speech recognition vocabulary perplexity and dynamically selecting acoustic models |
US5802149A (en) * | 1996-04-05 | 1998-09-01 | Lucent Technologies Inc. | On-line training of an automated-dialing directory |
US5983117A (en) * | 1996-06-21 | 1999-11-09 | Nortel Networks Corporation | System and method for interfacing a standard telephony device to a wireless communication system |
US6018568A (en) * | 1996-09-25 | 2000-01-25 | At&T Corp. | Voice dialing system |
US5915001A (en) * | 1996-11-14 | 1999-06-22 | Vois Corporation | System and method for providing and using universally accessible voice and speech data files |
US6154526A (en) * | 1996-12-04 | 2000-11-28 | Intellivoice Communications, Inc. | Data acquisition and error correcting speech recognition system |
US6665639B2 (en) | 1996-12-06 | 2003-12-16 | Sensory, Inc. | Speech recognition in consumer electronic products |
TW391092B (en) | 1996-12-27 | 2000-05-21 | Hitachi Ltd | Cellular mobile telephone apparatus and method for transmitting a response message to an caller |
US6823182B1 (en) | 1996-12-27 | 2004-11-23 | Hitachi, Ltd. | Cellular mobile telephone apparatus |
US6377663B1 (en) | 1997-01-03 | 2002-04-23 | Ncr Corporation | Call management system and associated method for a local telephone circuit |
US6775264B1 (en) | 1997-03-03 | 2004-08-10 | Webley Systems, Inc. | Computer, internet and telecommunications based network |
US6308062B1 (en) * | 1997-03-06 | 2001-10-23 | Ericsson Business Networks Ab | Wireless telephony system enabling access to PC based functionalities |
US5991364A (en) * | 1997-03-27 | 1999-11-23 | Bell Atlantic Network Services, Inc. | Phonetic voice activated dialing |
GB2325112B (en) * | 1997-05-06 | 2002-07-31 | Ibm | Voice processing system |
US6163596A (en) * | 1997-05-23 | 2000-12-19 | Hotas Holdings Ltd. | Phonebook |
US5924070A (en) * | 1997-06-06 | 1999-07-13 | International Business Machines Corporation | Corporate voice dialing with shared directories |
US5897616A (en) | 1997-06-11 | 1999-04-27 | International Business Machines Corporation | Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases |
US6298250B1 (en) | 1997-06-19 | 2001-10-02 | Kimberly Nanette Engen | Wireless prepaid telephone system with extended capability |
US6308053B1 (en) | 1997-06-19 | 2001-10-23 | Byard G. Nilsson | Recyclable wireless telephone unit with a secured activation switch |
US6292675B1 (en) | 1997-10-21 | 2001-09-18 | Byard G. Nilsson | Wireless mobile telephone system with voice-dialing telephone instruments and DTMF capability |
US6993321B1 (en) | 1997-06-19 | 2006-01-31 | Nilsson Byard G | Wireless telephone system with mobile instruments for outgoing calls |
US6751482B1 (en) | 1997-06-19 | 2004-06-15 | Byard G. Nilsson | Wireless mobile telephone system with alternative power instruments and DTMF Capability |
US6049710A (en) * | 1997-06-19 | 2000-04-11 | Kimberley Nanette Engen | Wireless prepaid telephone system with dispensable instruments |
US6862463B1 (en) | 1997-06-19 | 2005-03-01 | Byard G. Nilsson | Wireless telephone system with information service |
US6473610B1 (en) | 1997-06-19 | 2002-10-29 | Byard G. Nilsson | Wireless prepaid telephone system with dispensable instruments |
FI972723A0 (en) * | 1997-06-24 | 1997-06-24 | Nokia Mobile Phones Ltd | Mobile communications services |
FI973093A (en) * | 1997-07-23 | 1999-01-24 | Nokia Mobile Phones Ltd | A method for controlling a teleservice and a terminal |
US6052579A (en) * | 1997-07-29 | 2000-04-18 | Mcc Estabrook; David | Methods and apparatus for improved cellular communication |
KR19990016465A (en) * | 1997-08-16 | 1999-03-05 | 구자홍 | Theft prevention method of mobile communication terminal |
DE19738339C2 (en) * | 1997-09-02 | 2000-08-31 | Siemens Ag | Method for the user-controlled clearing down of wireless telecommunication connections in wireless telecommunication systems, in particular DECT systems |
DE19739792A1 (en) * | 1997-09-10 | 1999-03-11 | Siemens Ag | Decentralized execution of functions / services of a mobile radio system |
US5940799A (en) * | 1997-09-15 | 1999-08-17 | Motorola, Inc. | System and method for securing speech transactions |
DE69820222T2 (en) * | 1997-10-07 | 2004-09-30 | Koninklijke Philips Electronics N.V. | METHOD AND DEVICE FOR ACTIVATING A LANGUAGE-CONTROLLED FUNCTION IN A MULTIPLE NETWORK THROUGH BOTH SPEAKER-DEPENDENT AND SPEAKER-INDEPENDENT LANGUAGE RECOGNITION |
US6400940B1 (en) * | 1997-10-22 | 2002-06-04 | At&T Wireless Services, Inc. | Customized on line user guide |
US6035217A (en) * | 1997-10-29 | 2000-03-07 | Sony Corporation Of Japan | One button cellular phone, system, and method for use |
US6807256B1 (en) * | 1997-11-04 | 2004-10-19 | Bellsouth Intellectual Property Corporation | Call screening method and apparatus |
US6871064B1 (en) | 1997-11-04 | 2005-03-22 | Bellsouth Intellectual Property Corporation | Outgoing call handling system and method |
WO1999023802A1 (en) * | 1997-11-04 | 1999-05-14 | Bellsouth Intellectual Property Corporation | Outgoing call handling system and method |
US7280821B2 (en) * | 1998-10-27 | 2007-10-09 | At&T Bls Intellectual Property, Inc. | Outgoing call handling system and method |
US6075844A (en) * | 1997-11-18 | 2000-06-13 | At&T Corp. | Messaging system with remote messaging recording device where the message is routed based on the spoken name of the recipient |
DE19751170A1 (en) * | 1997-11-19 | 1999-06-02 | Bosch Gmbh Robert | Method for selecting a subscriber in a telecommunications network |
US6208959B1 (en) | 1997-12-15 | 2001-03-27 | Telefonaktibolaget Lm Ericsson (Publ) | Mapping of digital data symbols onto one or more formant frequencies for transmission over a coded voice channel |
FI974584A0 (en) * | 1997-12-19 | 1997-12-19 | Nokia Telecommunications Oy | Accelererad samtalsuppkoppling |
US6246987B1 (en) * | 1998-02-04 | 2001-06-12 | Alcatel Usa Sourcing, L.P. | System for permitting access to a common resource in response to speaker identification and verification |
US6154662A (en) * | 1998-02-27 | 2000-11-28 | Lucent Technologies Inc. | Providing voice dialing service for wireless roamers |
US6144723A (en) * | 1998-03-24 | 2000-11-07 | Nortel Networks Corporation | Method and apparatus for providing voice assisted call management in a telecommunications network |
US6163765A (en) * | 1998-03-30 | 2000-12-19 | Motorola, Inc. | Subband normalization, transformation, and voiceness to recognize phonemes for text messaging in a radio communication system |
US6154465A (en) * | 1998-10-06 | 2000-11-28 | Vertical Networks, Inc. | Systems and methods for multiple mode voice and data communications using intelligenty bridged TDM and packet buses and methods for performing telephony and data functions using the same |
US7072330B2 (en) * | 1998-04-03 | 2006-07-04 | Consolidated Ip Holdings, Inc. | Systems for voice and data communications having TDM and packet buses and telephony station cards including voltage generators |
CA2326894C (en) | 1998-04-03 | 2010-07-13 | Vertical Networks Inc. | Voice and data apparatus comprising a selective tapping digital signal processing resource |
US20090059818A1 (en) * | 1998-04-03 | 2009-03-05 | Pickett Scott K | Systems and methods for providing configurable caller id iformation |
US6181694B1 (en) | 1998-04-03 | 2001-01-30 | Vertical Networks, Inc. | Systems and methods for multiple mode voice and data communciations using intelligently bridged TDM and packet buses |
US6343074B1 (en) | 1998-09-29 | 2002-01-29 | Vertical Networks, Inc. | Systems and methods for multiple mode voice and data communications using intelligenty bridged TDM and packet buses and methods for performing telephony and data functions using the same |
US6266340B1 (en) | 1998-04-03 | 2001-07-24 | Vertical Networks, Inc. | Systems and methods for multiple voice data communication which includes interface cards including configurable clocks that are dynamically coupled to a TDS bus |
US6389009B1 (en) | 2000-12-28 | 2002-05-14 | Vertical Networks, Inc. | Systems and methods for multiple mode voice and data communications using intelligently bridged TDM and packet buses |
US6498791B2 (en) | 1998-04-03 | 2002-12-24 | Vertical Networks, Inc. | Systems and methods for multiple mode voice and data communications using intelligently bridged TDM and packet buses and methods for performing telephony and data functions using the same |
US6138100A (en) * | 1998-04-14 | 2000-10-24 | At&T Corp. | Interface for a voice-activated connection system |
US7548610B2 (en) * | 1998-04-14 | 2009-06-16 | Alaven, Inc. | Voice-activated geographically based telephone routing system and method |
US6240303B1 (en) | 1998-04-23 | 2001-05-29 | Motorola Inc. | Voice recognition button for mobile telephones |
US6151572A (en) * | 1998-04-27 | 2000-11-21 | Motorola, Inc. | Automatic and attendant speech to text conversion in a selective call radio system and method |
US6222917B1 (en) * | 1998-05-13 | 2001-04-24 | Nortel Dasa Network Systems Gmbh & Co. | Method and apparatus for providing a directory number to a call-processing device in a communications network |
US6229880B1 (en) * | 1998-05-21 | 2001-05-08 | Bell Atlantic Network Services, Inc. | Methods and apparatus for efficiently providing a communication system with speech recognition capabilities |
US6233315B1 (en) | 1998-05-21 | 2001-05-15 | Bell Atlantic Network Services, Inc. | Methods and apparatus for increasing the utility and interoperability of peripheral devices in communications systems |
US6073094A (en) * | 1998-06-02 | 2000-06-06 | Motorola | Voice compression by phoneme recognition and communication of phoneme indexes and voice features |
FR2781110B1 (en) * | 1998-07-13 | 2000-08-11 | Alsthom Cge Alcatel | METHOD AND DEVICE FOR TRANSMITTING DATA OVER A SPOKEN CHANNEL |
US6519699B2 (en) * | 1998-08-07 | 2003-02-11 | International Business Machines Corporation | Method and system for voice guided secure entry of private data in a public setting |
US6496571B1 (en) * | 1998-08-28 | 2002-12-17 | Lucent Technologies Inc. | Telecommunication system, method and telephone with personal caller identification capability |
US9037451B2 (en) * | 1998-09-25 | 2015-05-19 | Rpx Corporation | Systems and methods for multiple mode voice and data communications using intelligently bridged TDM and packet buses and methods for implementing language capabilities using the same |
US7274928B2 (en) * | 1998-10-02 | 2007-09-25 | Telespree Communications | Portable cellular phone system having automatic initialization |
US6167251A (en) * | 1998-10-02 | 2000-12-26 | Telespree Communications | Keyless portable cellular phone system having remote voice recognition |
US7003463B1 (en) * | 1998-10-02 | 2006-02-21 | International Business Machines Corporation | System and method for providing network coordinated conversational services |
US6445682B1 (en) | 1998-10-06 | 2002-09-03 | Vertical Networks, Inc. | Systems and methods for multiple mode voice and data communications using intelligently bridged TDM and packet buses and methods for performing telephony and data functions using the same |
JP2000196730A (en) * | 1998-12-25 | 2000-07-14 | Nec Saitama Ltd | Radio communication equipment |
US20060015638A1 (en) * | 1998-12-28 | 2006-01-19 | Holzhauser Lisa D | Method and apparatus for initiating telephone call from a mobile device |
US6744860B1 (en) | 1998-12-31 | 2004-06-01 | Bell Atlantic Network Services | Methods and apparatus for initiating a voice-dialing operation |
US6324507B1 (en) * | 1999-02-10 | 2001-11-27 | International Business Machines Corp. | Speech recognition enrollment for non-readers and displayless devices |
US6615045B1 (en) | 1999-03-03 | 2003-09-02 | Lucent Technologies Inc. | Method for transferring data upon request using permanent identifier |
US6810261B1 (en) * | 1999-03-03 | 2004-10-26 | Lucent Technologies Inc. | Method for transferring data using expanded permanent identifier |
US6748227B1 (en) | 1999-03-03 | 2004-06-08 | Lucent Technologies Inc. | Method for transferring data using permanent identifier including routing information |
US6603974B1 (en) * | 1999-03-03 | 2003-08-05 | Lucent Technologies Inc. | Method for transferring data |
US6404859B1 (en) * | 1999-03-16 | 2002-06-11 | Lockheed Martin Corporation | Voice enabled system for remote access of information |
US6526292B1 (en) * | 1999-03-26 | 2003-02-25 | Ericsson Inc. | System and method for creating a digit string for use by a portable phone |
US7260187B1 (en) | 1999-05-11 | 2007-08-21 | Verizon Services Corp. | Voice response apparatus and method of providing automated voice responses with silent prompting |
US7283964B1 (en) | 1999-05-21 | 2007-10-16 | Winbond Electronics Corporation | Method and apparatus for voice controlled devices with improved phrase storage, use, conversion, transfer, and recognition |
US6292781B1 (en) * | 1999-05-28 | 2001-09-18 | Motorola | Method and apparatus for facilitating distributed speech processing in a communication system |
KR100345537B1 (en) * | 1999-07-27 | 2002-07-26 | 삼성전자 주식회사 | Transmitting/receiving voice and key tone level control method for cellular phone |
US6356868B1 (en) * | 1999-10-25 | 2002-03-12 | Comverse Network Systems, Inc. | Voiceprint identification system |
US7392185B2 (en) | 1999-11-12 | 2008-06-24 | Phoenix Solutions, Inc. | Speech based learning/training system using semantic decoding |
US7050977B1 (en) | 1999-11-12 | 2006-05-23 | Phoenix Solutions, Inc. | Speech-enabled server for internet website and method |
US9076448B2 (en) | 1999-11-12 | 2015-07-07 | Nuance Communications, Inc. | Distributed real time speech recognition system |
US7725307B2 (en) | 1999-11-12 | 2010-05-25 | Phoenix Solutions, Inc. | Query engine for processing voice based queries including semantic decoding |
FR2802747B1 (en) * | 1999-12-16 | 2002-03-15 | Cit Alcatel | METHOD OF CALLING WITH A MOBILE TELEPHONE AS WELL AS SERVER CENTER AND RADIO COMMUNICATION TERMINAL FOR IMPLEMENTING THE PROCESS |
GB2358987B (en) * | 2000-02-01 | 2003-10-29 | Ericsson Telefon Ab L M | Electronic devices |
US6721705B2 (en) | 2000-02-04 | 2004-04-13 | Webley Systems, Inc. | Robust voice browser system and voice activated device controller |
US7516190B2 (en) | 2000-02-04 | 2009-04-07 | Parus Holdings, Inc. | Personal voice-based information retrieval system |
US6853714B2 (en) * | 2000-02-25 | 2005-02-08 | Keith A. Liljestrand | Apparatus and method for providing enhanced telecommunications services |
US6868070B1 (en) | 2000-10-06 | 2005-03-15 | Vertical Networks, Inc. | Systems and methods for providing voice/data communication systems and voice/data communications |
US6845251B2 (en) * | 2000-11-29 | 2005-01-18 | Visteon Global Technologies, Inc. | Advanced voice recognition phone interface for in-vehicle speech recognition applications |
US6915262B2 (en) | 2000-11-30 | 2005-07-05 | Telesector Resources Group, Inc. | Methods and apparatus for performing speech recognition and using speech recognition results |
US8135589B1 (en) * | 2000-11-30 | 2012-03-13 | Google Inc. | Performing speech recognition over a network and using speech recognition results |
US7203651B2 (en) | 2000-12-07 | 2007-04-10 | Art-Advanced Recognition Technologies, Ltd. | Voice control system with multiple voice recognition engines |
US6731724B2 (en) * | 2001-01-22 | 2004-05-04 | Pumatech, Inc. | Voice-enabled user interface for voicemail systems |
US7735021B2 (en) * | 2001-02-16 | 2010-06-08 | Microsoft Corporation | Shortcut system for use in a mobile electronic device and method thereof |
US7177402B2 (en) * | 2001-03-01 | 2007-02-13 | Applied Voice & Speech Technologies, Inc. | Voice-activated interactive multimedia information processing system |
US7366673B2 (en) * | 2001-06-15 | 2008-04-29 | International Business Machines Corporation | Selective enablement of speech recognition grammars |
US6892051B2 (en) * | 2001-06-25 | 2005-05-10 | Cingular Wireless Ii, Llc | System and method for providing an adapter module |
US6889065B2 (en) * | 2001-06-25 | 2005-05-03 | Cingular Wireless Ii, Llc | System and method for providing an adapter module |
US6898568B2 (en) * | 2001-07-13 | 2005-05-24 | Innomedia Pte Ltd | Speaker verification utilizing compressed audio formants |
FR2828042B1 (en) * | 2001-07-25 | 2004-07-09 | France Telecom | ACCESS CONTROL METHOD AND SYSTEM |
US20020010715A1 (en) * | 2001-07-26 | 2002-01-24 | Garry Chinn | System and method for browsing using a limited display device |
KR100418113B1 (en) * | 2001-09-07 | 2004-02-11 | 주식회사 엠보이스텔레소프트 | Special Communication System using Speech Recognition and Communication Service Providing Method using the same |
US6985865B1 (en) | 2001-09-26 | 2006-01-10 | Sprint Spectrum L.P. | Method and system for enhanced response to voice commands in a voice command platform |
US7050976B1 (en) | 2001-09-26 | 2006-05-23 | Sprint Spectrum L.P. | Method and system for use of navigation history in a voice command platform |
US7436939B1 (en) | 2001-09-26 | 2008-10-14 | Sprint Spectrum L.P. | Method and system for consolidated message notification in a voice command platform |
US7117159B1 (en) * | 2001-09-26 | 2006-10-03 | Sprint Spectrum L.P. | Method and system for dynamic control over modes of operation of voice-processing in a voice command platform |
US7313525B1 (en) | 2001-09-26 | 2007-12-25 | Sprint Spectrum L.P. | Method and system for bookmarking navigation points in a voice command title platform |
US6963760B2 (en) * | 2001-10-01 | 2005-11-08 | General Motors Corporation | Method and apparatus for generating DTMF tones using voice-recognition commands during hands-free communication in a vehicle |
US7113572B2 (en) * | 2001-10-03 | 2006-09-26 | Cingular Wireless Ii, Llc | System and method for recognition of and automatic connection using spoken address information received in voice mails and live telephone conversations |
US7085709B2 (en) * | 2001-10-30 | 2006-08-01 | Comverse, Inc. | Method and system for pronoun disambiguation |
US7295982B1 (en) | 2001-11-19 | 2007-11-13 | At&T Corp. | System and method for automatic verification of the understandability of speech |
US20040054538A1 (en) * | 2002-01-03 | 2004-03-18 | Peter Kotsinadelis | My voice voice agent for use with voice portals and related products |
US7286651B1 (en) | 2002-02-12 | 2007-10-23 | Sprint Spectrum L.P. | Method and system for multi-modal interaction |
US7203652B1 (en) | 2002-02-21 | 2007-04-10 | Nuance Communications | Method and system for improving robustness in a speech system |
US7197301B2 (en) * | 2002-03-04 | 2007-03-27 | Telespree Communications | Method and apparatus for secure immediate wireless access in a telecommunications network |
US8046581B2 (en) * | 2002-03-04 | 2011-10-25 | Telespree Communications | Method and apparatus for secure immediate wireless access in a telecommunications network |
US6870915B2 (en) * | 2002-03-20 | 2005-03-22 | Bellsouth Intellectual Property Corporation | Personal address updates using directory assistance data |
US6999564B1 (en) * | 2002-03-29 | 2006-02-14 | Nortel Networks Limited | System and method for telephonic switching and signaling based on voice recognition |
US20030191646A1 (en) * | 2002-04-08 | 2003-10-09 | D'avello Robert F. | Method of setting voice processing parameters in a communication device |
US6792096B2 (en) | 2002-04-11 | 2004-09-14 | Sbc Technology Resources, Inc. | Directory assistance dialog with configuration switches to switch from automated speech recognition to operator-assisted dialog |
US7180994B2 (en) | 2002-06-13 | 2007-02-20 | Volt Information Sciences, Inc. | Method and system for operator services automation using an operator services switch |
US7224981B2 (en) * | 2002-06-20 | 2007-05-29 | Intel Corporation | Speech recognition of mobile devices |
US7706359B2 (en) * | 2002-07-01 | 2010-04-27 | Converged Data Solutions, Inc. | Systems and methods for voice and data communications including a network drop and insert interface for an external data routing resource |
US7869424B2 (en) * | 2002-07-01 | 2011-01-11 | Converged Data Solutions Inc. | Systems and methods for voice and data communications including a scalable TDM switch/multiplexer |
US20040005914A1 (en) * | 2002-07-08 | 2004-01-08 | Dear Jean Paul | Wireless communicator with integral display |
US7464035B2 (en) * | 2002-07-24 | 2008-12-09 | Robert Bosch Corporation | Voice control of home automation systems via telephone |
US7164934B2 (en) * | 2003-01-30 | 2007-01-16 | Hoyt Technologies, Inc. | Mobile telephone having voice recording, playback and automatic voice dial pad |
US20040170265A1 (en) * | 2003-02-27 | 2004-09-02 | Benco David S. | Conference call security |
EP1632081B1 (en) * | 2003-05-23 | 2016-08-17 | Kirusa, Inc. | A method and system for communicating a data file over a network and teleconferencing over a telephony network |
WO2004114207A2 (en) * | 2003-05-24 | 2004-12-29 | Gatelinx Corporation | Artificial intelligence dialogue processor |
US7243072B2 (en) * | 2003-06-27 | 2007-07-10 | Motorola, Inc. | Providing assistance to a subscriber device over a network |
ATE410768T1 (en) * | 2003-08-29 | 2008-10-15 | Johnson Controls Tech Co | SYSTEM AND METHOD FOR OPERATING A VOICE RECOGNITION SYSTEM IN A VEHICLE |
KR100595610B1 (en) * | 2003-10-29 | 2006-06-30 | 엘지전자 주식회사 | Guidance method and apparatus for telephone number |
US7515695B1 (en) | 2003-12-15 | 2009-04-07 | Avaya Inc. | Client customizable interactive voice response system |
US7426585B1 (en) * | 2004-01-22 | 2008-09-16 | Quartet Technology, Inc. | Smart cables |
CN1989733A (en) * | 2004-05-21 | 2007-06-27 | 电缆优势软件有限公司 | Remote access system and method and intelligent agent therefor |
US8130929B2 (en) * | 2004-05-25 | 2012-03-06 | Galileo Processing, Inc. | Methods for obtaining complex data in an interactive voice response system |
US20060009974A1 (en) * | 2004-07-09 | 2006-01-12 | Matsushita Electric Industrial Co., Ltd. | Hands-free voice dialing for portable and remote devices |
SE0401952L (en) * | 2004-07-29 | 2006-01-30 | Klas Greger Eriksson | Mobile phone system related arrangement |
US7580837B2 (en) | 2004-08-12 | 2009-08-25 | At&T Intellectual Property I, L.P. | System and method for targeted tuning module of a speech recognition system |
US7724889B2 (en) * | 2004-11-29 | 2010-05-25 | At&T Intellectual Property I, L.P. | System and method for utilizing confidence levels in automated call routing |
US7242751B2 (en) | 2004-12-06 | 2007-07-10 | Sbc Knowledge Ventures, L.P. | System and method for speech recognition-enabled automatic call routing |
US7751551B2 (en) | 2005-01-10 | 2010-07-06 | At&T Intellectual Property I, L.P. | System and method for speech-enabled call routing |
US20080069327A1 (en) * | 2005-02-08 | 2008-03-20 | Kingsley Christopher G | Apparatus and method for providing enhanced telecommunications services |
US8223954B2 (en) | 2005-03-22 | 2012-07-17 | At&T Intellectual Property I, L.P. | System and method for automating customer relations in a communications environment |
US7657020B2 (en) * | 2005-06-03 | 2010-02-02 | At&T Intellectual Property I, Lp | Call routing system and method of using the same |
US20070136069A1 (en) * | 2005-12-13 | 2007-06-14 | General Motors Corporation | Method and system for customizing speech recognition in a mobile vehicle communication system |
JP4466572B2 (en) * | 2006-01-16 | 2010-05-26 | コニカミノルタビジネステクノロジーズ株式会社 | Image forming apparatus, voice command execution program, and voice command execution method |
US20070233481A1 (en) * | 2006-04-03 | 2007-10-04 | Texas Instruments Inc. | System and method for developing high accuracy acoustic models based on an implicit phone-set determination-based state-tying technique |
US8285654B2 (en) * | 2006-06-29 | 2012-10-09 | Nathan Bajrach | Method and system of providing a personalized performance |
US8536976B2 (en) * | 2008-06-11 | 2013-09-17 | Veritrix, Inc. | Single-channel multi-factor authentication |
US8006291B2 (en) | 2008-05-13 | 2011-08-23 | Veritrix, Inc. | Multi-channel multi-factor authentication |
US8468358B2 (en) | 2010-11-09 | 2013-06-18 | Veritrix, Inc. | Methods for identifying the guarantor of an application |
US8516562B2 (en) | 2008-05-13 | 2013-08-20 | Veritrix, Inc. | Multi-channel multi-factor authentication |
US8166297B2 (en) | 2008-07-02 | 2012-04-24 | Veritrix, Inc. | Systems and methods for controlling access to encrypted data stored on a mobile device |
WO2010051342A1 (en) | 2008-11-03 | 2010-05-06 | Veritrix, Inc. | User authentication for social networks |
JP4811507B2 (en) * | 2009-08-25 | 2011-11-09 | コニカミノルタビジネステクノロジーズ株式会社 | Image processing system, image processing apparatus, and information processing apparatus |
WO2011050386A1 (en) * | 2009-10-27 | 2011-05-05 | Andre Krause | A shared advertised contact number with multiple sound recordings |
US10032455B2 (en) | 2011-01-07 | 2018-07-24 | Nuance Communications, Inc. | Configurable speech recognition system using a pronunciation alignment between multiple recognizers |
US8474014B2 (en) | 2011-08-16 | 2013-06-25 | Veritrix, Inc. | Methods for the secure use of one-time passwords |
US9355174B2 (en) | 2012-09-07 | 2016-05-31 | Iheartmedia Management Services, Inc. | Multi-input playlist selection |
CN104769668B (en) | 2012-10-04 | 2018-10-30 | 纽昂斯通讯公司 | The improved mixture control for ASR |
US9691377B2 (en) | 2013-07-23 | 2017-06-27 | Google Technology Holdings LLC | Method and device for voice recognition training |
US9275638B2 (en) | 2013-03-12 | 2016-03-01 | Google Technology Holdings LLC | Method and apparatus for training a voice recognition model database |
US9548047B2 (en) | 2013-07-31 | 2017-01-17 | Google Technology Holdings LLC | Method and apparatus for evaluating trigger phrase enrollment |
US9344419B2 (en) | 2014-02-27 | 2016-05-17 | K.Y. Trix Ltd. | Methods of authenticating users to a site |
US9953646B2 (en) | 2014-09-02 | 2018-04-24 | Belleau Technologies | Method and system for dynamic speech recognition and tracking of prewritten script |
US10971157B2 (en) | 2017-01-11 | 2021-04-06 | Nuance Communications, Inc. | Methods and apparatus for hybrid speech recognition processing |
US11627012B2 (en) | 2018-10-09 | 2023-04-11 | NewTekSol, LLC | Home automation management system |
CN111045641B (en) * | 2019-12-13 | 2022-03-25 | 合肥联宝信息技术有限公司 | Electronic terminal and voice recognition method |
Family Cites Families (79)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3673331A (en) * | 1970-01-19 | 1972-06-27 | Texas Instruments Inc | Identity verification by voice signals in the frequency domain |
US3928424A (en) | 1973-03-05 | 1975-12-23 | Du Pont | Mixed esters of dibasic unsaturated acids, glycols and glycidyl esters |
US3928724A (en) * | 1974-10-10 | 1975-12-23 | Andersen Byram Kouma Murphy Lo | Voice-actuated telephone directory-assistance system |
US4122306A (en) | 1975-11-24 | 1978-10-24 | Jacob Friedman | Telephone answering apparatus providing selective message communication |
JPS6057261B2 (en) * | 1980-03-18 | 1985-12-13 | 日本電気株式会社 | Multi-line audio input/output device |
US4348550A (en) | 1980-06-09 | 1982-09-07 | Bell Telephone Laboratories, Incorporated | Spoken word controlled automatic dialer |
JPS58138134A (en) | 1982-02-12 | 1983-08-16 | Nissan Motor Co Ltd | Car telephone set |
US4400584A (en) | 1982-04-05 | 1983-08-23 | Motorola, Inc. | Speakerphone for radio and, landline telephones |
US4587670A (en) * | 1982-10-15 | 1986-05-06 | At&T Bell Laboratories | Hidden Markov model speech recognition arrangement |
US4625081A (en) | 1982-11-30 | 1986-11-25 | Lotito Lawrence A | Automated telephone voice service system |
US4468813A (en) | 1982-12-06 | 1984-08-28 | Motorola, Inc. | Digital voice storage system |
JPS6081034A (en) | 1983-10-05 | 1985-05-09 | Seiko Epson Corp | Manufacture of base material for optical fiber |
JPS6085655A (en) | 1983-10-15 | 1985-05-15 | Fujitsu Ten Ltd | Voice dialing device |
JPS60119159A (en) | 1983-11-30 | 1985-06-26 | Toshiba Corp | Radiotelephonic device |
FR2559325B1 (en) | 1984-02-06 | 1986-08-22 | Renault | APPARATUS FOR CAPTURING AND TRANSMITTING THE WORD OF A PERSON PLACED IN A DISTURBED ENVIRONMENT IN ORDER TO PERFORM A PROCESSING OF THIS WORD |
FR2571191B1 (en) | 1984-10-02 | 1986-12-26 | Renault | RADIOTELEPHONE SYSTEM, PARTICULARLY FOR MOTOR VEHICLE |
US4644107A (en) * | 1984-10-26 | 1987-02-17 | Ttc | Voice-controlled telephone using visual display |
DE3519972A1 (en) * | 1985-06-04 | 1986-12-04 | Licentia Patent-Verwaltungs-Gmbh, 6000 Frankfurt | Radiopaging arrangement with additional transmission of numerical information |
US4737976A (en) * | 1985-09-03 | 1988-04-12 | Motorola, Inc. | Hands-free control system for a radiotelephone |
US5182765A (en) * | 1985-11-26 | 1993-01-26 | Kabushiki Kaisha Toshiba | Speech recognition system with an accurate recognition function |
US4873714A (en) | 1985-11-26 | 1989-10-10 | Kabushiki Kaisha Toshiba | Speech recognition system with an accurate recognition function |
US4698839A (en) * | 1986-06-03 | 1987-10-06 | Devaney David B | Mobile telephone switching office |
US4827500A (en) | 1987-01-30 | 1989-05-02 | American Telephone And Telegraph Company, At&T Bell Laboratories | Automatic speech recognition to select among call destinations |
GB8702910D0 (en) * | 1987-02-10 | 1987-03-18 | British Telecomm | Multi-user speech recognition system |
US4959850A (en) | 1987-05-29 | 1990-09-25 | Kabushiki Kaisha Toshiba | Radio telephone apparatus |
EP0293259A3 (en) * | 1987-05-29 | 1990-03-07 | Kabushiki Kaisha Toshiba | Voice recognition system used in telephone apparatus |
DE3819538C3 (en) * | 1987-06-08 | 1996-08-14 | Ricoh Kk | Voice activated dialer |
US5003576A (en) | 1987-07-24 | 1991-03-26 | Richard J. Helferich | Analog/digital voice storage cellular telephone |
USRE34976E (en) | 1987-07-24 | 1995-06-20 | Richard J. Helferich | Analog/digital voice storage cellular telephone |
DE3885683T2 (en) * | 1987-09-11 | 1994-03-10 | Toshiba Kawasaki Kk | Telephone. |
JPS6477353A (en) | 1987-09-18 | 1989-03-23 | Toshiba Corp | Land mobile telephone system |
US4945570A (en) | 1987-10-02 | 1990-07-31 | Motorola, Inc. | Method for terminating a telephone call by voice command |
EP0311414B2 (en) | 1987-10-08 | 1997-03-12 | Nec Corporation | Voice controlled dialer having memories for full-digit dialing for any users and abbreviated dialing for authorized users |
US4870686A (en) * | 1987-10-19 | 1989-09-26 | Motorola, Inc. | Method for entering digit sequences by voice command |
US4928302A (en) | 1987-11-06 | 1990-05-22 | Ricoh Company, Ltd. | Voice actuated dialing apparatus |
US5199062A (en) * | 1988-01-20 | 1993-03-30 | Phone Base Systems Inc. | Telephone communications system including a digital telephone switch, a voice response unit and a stored program sequence for controlling both the switch and the voice response unit |
JP2751244B2 (en) | 1988-02-18 | 1998-05-18 | 日本電気株式会社 | Hands-free circuit and hands-free control method |
GB8809898D0 (en) * | 1988-04-27 | 1988-06-02 | British Telecomm | Voice-operated service |
US5117460A (en) | 1988-06-30 | 1992-05-26 | Motorola, Inc. | Voice controlled pager and programming techniques therefor |
US5040212A (en) | 1988-06-30 | 1991-08-13 | Motorola, Inc. | Methods and apparatus for programming devices to recognize voice commands |
US5119417A (en) | 1988-07-20 | 1992-06-02 | Casio Computer Co., Ltd. | Auto-dialing apparatus |
US4961216A (en) | 1988-12-30 | 1990-10-02 | Baehr G Geoffrey | Telephone answering and paging system |
JPH02209055A (en) | 1989-02-09 | 1990-08-20 | Toshiba Corp | Telephone set |
KR920001542B1 (en) | 1989-02-28 | 1992-02-18 | 삼성전자 주식회사 | Automatic answering method for a vehicle radio-telephone and device therefor |
US5109400A (en) | 1989-04-28 | 1992-04-28 | Motorola, Inc. | Communication system with registration and two way radio |
JP2927891B2 (en) * | 1989-06-19 | 1999-07-28 | 日本電気株式会社 | Voice dialing device |
US5148471A (en) * | 1989-11-20 | 1992-09-15 | Motorola, Inc. | Communications device with voice recognition and movable element control interface |
US5020107A (en) | 1989-12-04 | 1991-05-28 | Motorola, Inc. | Limited vocabulary speech recognition system |
US5095503A (en) | 1989-12-20 | 1992-03-10 | Motorola, Inc. | Cellular telephone controller with synthesized voice feedback for directory number confirmation and call status |
US5420918A (en) | 1990-03-20 | 1995-05-30 | Canon Kabushiki Kaisha | Telephone apparatus for invalidating incoming call signals during dialing |
US5187735A (en) * | 1990-05-01 | 1993-02-16 | Tele Guia Talking Yellow Pages, Inc. | Integrated voice-mail based voice and information processing system |
US5127043A (en) * | 1990-05-15 | 1992-06-30 | Vcs Industries, Inc. | Simultaneous speaker-independent voice recognition and verification over a telephone network |
US5365574A (en) * | 1990-05-15 | 1994-11-15 | Vcs Industries, Inc. | Telephone network voice recognition and verification using selectively-adjustable signal thresholds |
US5303299A (en) * | 1990-05-15 | 1994-04-12 | Vcs Industries, Inc. | Method for continuous recognition of alphanumeric strings spoken over a telephone network |
US5301223A (en) * | 1990-05-22 | 1994-04-05 | Cellular Technical Services Company, Inc. | Cellular telephone system with remote programming, voice responsive registration and real time billing |
JP2523945B2 (en) * | 1990-05-30 | 1996-08-14 | 松下電器産業株式会社 | Answering machine |
US5077785A (en) | 1990-07-13 | 1991-12-31 | Monson Gerald D | System for recording comments by patrons of establishments |
JPH04235630A (en) | 1990-07-30 | 1992-08-24 | Ronald L Colier | Method and device for conducting programming of computer by audible command |
US5131029A (en) | 1990-08-23 | 1992-07-14 | Kunstadt George H | Cellular car telephone dialing controller |
DE69131088T2 (en) | 1990-09-11 | 1999-11-11 | Alcatel Usa Sourcing Lp | Process for integrated voice communication |
US5193110A (en) * | 1990-10-09 | 1993-03-09 | Boston Technology, Incorporated | Integrated services platform for telephone communication system |
US5274695A (en) * | 1991-01-11 | 1993-12-28 | U.S. Sprint Communications Company Limited Partnership | System for verifying the identity of a caller in a telecommunications network |
WO1993001664A1 (en) * | 1991-07-08 | 1993-01-21 | Motorola, Inc. | Remote voice control system |
US5195090A (en) * | 1991-07-09 | 1993-03-16 | At&T Bell Laboratories | Wireless access telephone-to-telephone network interface architecture |
US5345501A (en) * | 1991-07-15 | 1994-09-06 | Bell Atlantic Network Services, Inc. | Telephone central office based method of and system for processing customer orders |
US5289530A (en) * | 1991-07-23 | 1994-02-22 | Morris Reese | Method and apparatus for vocally communicating to a caller at a remote telephone station synthesized speech of stored special service information |
US5208848A (en) * | 1991-08-26 | 1993-05-04 | At&T Bell Laboratories | Telecommunications call processing |
US5222125A (en) * | 1991-09-03 | 1993-06-22 | At&T Bell Laboratories | System for providing personalized telephone calling features |
US5283833A (en) * | 1991-09-19 | 1994-02-01 | At&T Bell Laboratories | Method and apparatus for speech processing using morphology and rhyming |
US5390278A (en) * | 1991-10-08 | 1995-02-14 | Bell Canada | Phoneme based speech recognition |
US5335313A (en) * | 1991-12-03 | 1994-08-02 | Douglas Terry L | Voice-actuated, speaker-dependent control system for hospital bed |
US5353376A (en) * | 1992-03-20 | 1994-10-04 | Texas Instruments Incorporated | System and method for improved speech acquisition for hands-free voice telecommunication in a noisy environment |
US5297183A (en) * | 1992-04-13 | 1994-03-22 | Vcs Industries, Inc. | Speech recognition system for electronic switches in a cellular telephone or personal communication network |
US5315649A (en) * | 1992-04-15 | 1994-05-24 | Vcs Industries, Inc. | Toll call telephone service center |
US5353336A (en) * | 1992-08-24 | 1994-10-04 | At&T Bell Laboratories | Voice directed communications system archetecture |
US6049710A (en) * | 1997-06-19 | 2000-04-11 | Kimberley Nanette Engen | Wireless prepaid telephone system with dispensable instruments |
US6404884B1 (en) * | 1999-10-08 | 2002-06-11 | Grape Technology Group, Inc. | Personalized assistance system and method |
US6865403B1 (en) * | 2000-11-28 | 2005-03-08 | Sprint Spectrum L.P. | Method and system for simplified control of a subscriber terminal |
US20030181223A1 (en) * | 2002-03-25 | 2003-09-25 | Lucent Technologies Inc. | System and method for voice activated dialing |
-
1992
- 1992-04-13 US US07/867,873 patent/US5297183A/en not_active Expired - Lifetime
-
1993
- 1993-04-13 CA CA002118135A patent/CA2118135C/en not_active Expired - Fee Related
- 1993-04-13 ES ES93910598T patent/ES2156871T3/en not_active Expired - Lifetime
- 1993-04-13 DE DE69329850T patent/DE69329850T2/en not_active Expired - Lifetime
- 1993-04-13 EP EP93910598A patent/EP0636294B1/en not_active Expired - Lifetime
- 1993-04-13 AT AT93910598T patent/ATE198688T1/en not_active IP Right Cessation
- 1993-04-13 WO PCT/US1993/003491 patent/WO1993021721A1/en active IP Right Grant
- 1993-04-13 AU AU41032/93A patent/AU672202B2/en not_active Ceased
-
1994
- 1994-03-22 US US08/216,009 patent/US5659597A/en not_active Expired - Lifetime
-
1997
- 1997-08-19 US US08/914,440 patent/US6157848A/en not_active Expired - Fee Related
-
2000
- 2000-11-27 US US09/722,810 patent/US6501966B1/en not_active Expired - Fee Related
-
2002
- 2002-12-03 US US10/308,653 patent/US7551944B2/en not_active Expired - Fee Related
-
2008
- 2008-12-02 US US12/326,753 patent/US8019387B2/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
AU4103293A (en) | 1993-11-18 |
DE69329850D1 (en) | 2001-02-15 |
US6501966B1 (en) | 2002-12-31 |
US20030087675A1 (en) | 2003-05-08 |
US5659597A (en) | 1997-08-19 |
ATE198688T1 (en) | 2001-01-15 |
US5297183A (en) | 1994-03-22 |
DE69329850T2 (en) | 2001-07-19 |
US6157848A (en) | 2000-12-05 |
CA2118135A1 (en) | 1993-10-28 |
WO1993021721A1 (en) | 1993-10-28 |
ES2156871T3 (en) | 2001-08-01 |
US7551944B2 (en) | 2009-06-23 |
AU672202B2 (en) | 1996-09-26 |
US20090074157A1 (en) | 2009-03-19 |
EP0636294A4 (en) | 1997-01-29 |
US8019387B2 (en) | 2011-09-13 |
EP0636294A1 (en) | 1995-02-01 |
EP0636294B1 (en) | 2001-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2118135C (en) | Speech recognition system for electronic switches in a cellular telephone or personal communications network | |
EP0890249B1 (en) | Apparatus and method for reducing speech recognition vocabulary perplexity and dynamically selecting acoustic models | |
US5274695A (en) | System for verifying the identity of a caller in a telecommunications network | |
US5369685A (en) | Voice-activated telephone directory and call placement system | |
US5881134A (en) | Intelligent call processing platform for home telephone system | |
EP0477688B1 (en) | Voice recognition telephone dialing | |
US6931104B1 (en) | Intelligent call processing platform for home telephone system | |
US6556127B1 (en) | Speaker verification method | |
US5315649A (en) | Toll call telephone service center | |
US5802149A (en) | On-line training of an automated-dialing directory | |
KR930006035B1 (en) | Password controlled switching system | |
US20040247088A1 (en) | Automatic voice call connection service method using personal phone book databse constructed through voice recognition | |
US20020098833A1 (en) | Customized on-line user guide | |
EP1164576A1 (en) | Speaker authentication method and system from speech models | |
US20010011945A1 (en) | Dynamic virtual paging method and apparatus | |
CA2206870C (en) | Intelligent call processing platform for home telephone system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
EEER | Examination request | ||
MKLA | Lapsed | ||
MKLA | Lapsed |
Effective date: 20100413 |