WO2005046201A2 - Audio signature apparatus and methods - Google Patents

Abstract

Signature-based channel or program identification apparatus and methods for use with audio/video content delivery and distribution systems are disclosed. The disclosed apparatus and methods acquire peak signal magnitudes between zero crossings of a reference audio signal and an audio signal associated with audio/video content consumed at a consumption site. Signatures for the signals are developed using sums of the peak signal magnitudes and the signatures are compared to identify the audio/video content consumed at the consumption site.

Description

AUDIO SIGNATURE APPARATUS AND METHODS

RELATED APPLICATION [0001] This application claims the benefit ofthe filing date of U.S. Provisional Application No. 60/511,838, entitled "Audio Signature Apparatus and Methods" and filed on October 16, 2003, the entire disclosure of which is incorporated by reference herein in its entirety.

FIELD OF THE DISCLOSURE [0002] The present disclosure relates generally to audio/video content delivery and distribution systems and, more specifically, to audio signature apparatus and methods for use with audio/video content delivery and distribution systems. BACKGROUND [0003] Ratings information and/or audio/video content consumption information are typically generated by collecting consumption records (e.g., viewing records) or other information from a group of statistically selected households. Each ofthe statistically selected households typically has a data logging and processing unit commonly referred to as a "home unit" or "site unit." The site unit may communicate with a variety of attachments that provide inputs to the site unit or that receive outputs from the site unit. For example, in the case where the audio/video content being consumed consists of analog television broadcasts, a source identification unit such as a frequency detector attachment, which is a well-known device, may be in communication with a television to sense a local oscillator frequency ofthe television tuner. In this manner, the frequency detector attachment may be used to determine if the television is operating (i.e., is turned on) and to determine to which broadcast channel the television is currently tuned based on a detected frequency. Additionally, a people counter, which is also a well-known device, may be located in the consumption space ofthe television and in communication with the site unit, thereby enabling the site unit to detect the number of persons currently consuming programs displayed on the television.

[0004] The site unit usually processes the inputs (e.g., channel tuning information, number of viewers, etc.) from the attachments to produce audio/video content consumption records. Consumption records may be generated on a periodic basis (i.e., at fixed time intervals) or may be generated in response to a change in an input such as, for example, a change in the number ofthe persons viewing the television, a change in the channel tuning information (i.e., a channel change), etc. and may contain channel information such as a station or channel number and a time (e.g., a date and time of day) at which the channel was consumed in the case where the content being consumed is associated with a broadcast television program. In the case where the audio/video content being consumed is associated with a local audio/video content delivery device such as, for example, a digital versatile disk (DVD) player, a digital video recorder (DVR), a video cassette recorder (VCR), etc., the consumption records may include content identification (i.e., program identification) information as well as information relating to the time and manner in which the associated content was consumed. Of course, consumption records may contain other or additional information such as the number of viewers present at the viewing time. [0005] The site unit collects a quantity of consumption records and typically transmits collected records, usually daily, to a central office or central data processing facility for further processing or analysis. The central data processing facility receives consumption records from site units located in some or all ofthe statistically selected households and analyzes the records to ascertain the audio/video consumption behaviors of a particular household or a particular group of households selected from all participating households. Additionally, the central data processing facility may generate consumption behavior statistics and other parameters indicative of consumption behavior associated with some or all ofthe participating households. [0006] The rapid development and deployment of a wide variety of audio/video content delivery and distribution system technology platforms has dramatically complicated the site unit task of providing consumption records or information to the central data collection facility. For instance, while the above-mentioned frequency detector device can be used to detect channel information at a site where network television broadcasts are being consumed (because, under normal operation conditions, the local oscillator frequency corresponds to a known network channel), such a device typically cannot be used with digital broadcast systems. In particular, digital broadcast systems (e.g., satellite-based digital television systems, digital cable systems, etc.) typically include a digital receiver or set-top box at each subscriber site. The digital receiver or set-top box demodulates a multi-program data stream, parses the multi-program data stream into individual audio and/or video data packets, and selectively processes the data packets to generate an audio/video signal for a desired program. The audio and/or video output signals generated by the set-top box can typically be directly coupled to an audio/video input of an output device (e.g., a television, a video monitor, etc.) As a result, the local oscillator frequency ofthe output device tuner, if any, does not necessarily have any meaningful relationship to the channel or program currently being consumed. [0007] Similarly, obtaining consumption records or information is complicated in cases where the audio/video content being consumed is delivered via a local source such as, for example, a DVD player, a DVR, a VCR, or the like. Such local sources enable the same audio/video content to be viewed at various times in different manners across households, thereby precluding the use of a program lineup or the like at the central facility to identify consumed audio/video content based on channel and consumption time information and significantly complicating audio/video content identification at the central facility.

[0008] Some techniques for identifying consumed audio/video content are based on the use of audio and/or video signatures. In general, signature-based channel or audio/video content identification techniques use one or more characteristics of currently consumed (but not yet identified) audio/video content to generate a substantially unique signature (e.g., a series of digital values, a waveform, etc.) for that content. The signature information for the content being consumed is typically compared to signature information associated with known audio/video content. When a substantial match is found, the currently consumed audio/video content can, with a relatively high probability, be identified as the portion ofthe known audio/video content having substantially matching signature information. [0009] The use of audio signatures has proven to be particularly efficient for identifying audio/video content such as, for example, television broadcasts. In general, audio signature-based audio/video content identification techniques are computationally efficient and require less memory than known video signature-based techniques. Some known audio signature-based techniques use the root mean square (RMS) ofthe energy ofthe audio signal associated with a program as signature information. However, such RMS -based techniques do not consider the frequency of the audio signal being monitored and, as a result, may not provide a sufficiently high degree of content identification accuracy. Still other known audio signature-based techniques use the number of zero crossings between fixed time intervals to generate signature information. However, such count-based zero crossing audio signature techniques do not consider the magnitude ofthe audio signals being monitored and, thus, may not provide a sufficiently high degree of content identification accuracy. More generally, known computationally efficient audio signature-based program identification techniques are not sufficiently reliable because these known techniques typically ignore important distinguishing characteristics ofthe audio. As a result, such known techniques may limit or prevent the identification of audio/video content and/or may result in an incorrect identification of that content. BRIEF DESCRIPTION OF THE DRAWINGS [0010] Fig. 1 is a block diagram of an example system that uses audio signatures to identify audio/video content being consumed.

[0011] Fig. 2 is a more detailed block diagram that depicts an example manner in which the audio signature processor shown in Fig. 1 may be implemented. [0012] Fig. 3 is a more detailed block diagram that depicts an example manner in which the signature generators shown in Fig. 2 may be implemented. [0013] Fig. 4 is an example graph that depicts an audio signal that may be processed by the example signature generator shown in Fig. 3. [0014] Fig. 5 is an example graph that depicts zero crossing data that may be generated by the example audio signature processor of Fig. 1.

[0015] Fig. 6 is a block diagram that depicts another example manner in which the audio signature processor shown in Fig. 1 may be implemented. [0016] Fig. 7 is a flow diagram that depicts an example manner in which the apparatus shown in Fig. 6 may be configured to perform the audio signature processing functions described herein. [0017] Fig. 8 is a flow diagram that depicts an example manner in which the apparatus shown in Fig. 6 may be configured to perform the audio signature generation functions described herein.

[0018] Fig. 9 is another example manner in which the audio signature apparatus and methods described herein may be implemented. DETAILED DESCRIPTION [0019] Fig. 1 is a block diagram of an example system 10 that uses audio signatures to identify audio/video content. The example system 10 corresponds to an audio/video content consumption site such as, for example, a residence, a business location, or any other site at which video and/or audio programs may be consumed (e.g., viewed, listened to, etc.) For purposes of simplifying the discussion, Fig. 1 depicts a single system or consumption site 10. However, a plurality of consumption sites may be configured in manners similar or identical to that ofthe example system 10 to implement the audio signature apparatus and methods described herein. [0020] The example system 10 includes an output device 12 such as, for example, a television or a video monitor that receives an audio/video content signal 14. The signal 14 may be a broadcast signal transmitted by a broadcast station (not shown) such as, for example, a television station, radio station, etc. that transmits video programs, audio programs and/or other audio/video content or programs (e.g., television programs, advertisements, etc.) over a relatively wide geographic region to a plurality of viewers and/or subscribers. Alternatively, the signal 14 may be provided by one or more local audio/video content delivery device (e.g., DVRs, VCRs, etc.). In any case, the signal 14 may include one or more analog signals or information (e.g., conventional analog television transmissions), a digital data stream containing one or more video and/or audio programs in the form of data packets, or any desired combination thereof. The audio/video content signal 14 may be conveyed to the system 10 using any desired combination of wireless and hardwired links, including, for example, satellite links, cellular links, telephone lines, cable, the Internet, etc.

[0021] As shown in Fig. 1 , a receiver, decoder or set-top box 16 may be serially interposed between the broadcast signal 14 and the output device 12. For example, in the case where the broadcast signal 14 is a digital satellite or cable television transmission, the set-top box 16 demodulates the broadcast signal, demodulates multi- program data streams and selectively parses video and/or audio data packets associated with a desired channel and/or program. The selected data packets are processed to form an output signal 18 that can be output (e.g., displayed, played, etc.) by the output device 12. For example, in the case where the output device 12 is a television, the output signal 18 may be a composite video signal, an S-video signal, an RGB signal, or any other displayable video signal applied to the appropriate input connections ofthe output device 12. Of course, in the case where the signal 14 is a conventional analog television transmission or signal, the set-top box 16 may not be required and the signal 14 can be directly coupled to the output device 12 (e.g., directly coupled to UHF/VHF inputs). In addition to its signal processing functions, the set-top box 16 may also perform access control functions such as, for example, determining what programs are available for viewing by a user ofthe system 10 based on subscription status or subscription information associated with the system 10, generating displayable program guide information, etc. [0022] The example system 10 also includes an audio signature processor 20 that may be configured to perform audio signature generation, comparison and/or signature matching detection functions to determine what channel, program and/or audio/video content is currently being consumed via the output device 12. More specifically, the audio signature processor 20 receives the audio/video content signal 14 and an audio signal 22 from the output device- 12. The audio signal 22 contains audio information associated with the audio/video content currently being consumed via the output device 12 (e.g., the television channel and program to which the system 10 is currently tuned). Alternatively, the audio signature processor 20 may be coupled to an acoustic transducer 24 such as, for example, a microphone that is proximate to an acoustic output device (e.g., a speaker) associated with the output device 12. In that case, the acoustic transducer 24 supplies an audio signal 25 containing information associated with the program currently being consumed via the output device 12 instead ofthe audio signal 22.

[0023] As described in greater detail in connection with Figs. 2-9 below, the audio signature processor 20 may generate signatures or signature information (i.e., signature information that is associated with the audio/video content currently being consumed via the output device 12 and generated from the audio signal 22 or, alternatively, for the audio signal 25 provided by the acoustic transducer 24), and reference signatures or signature information from the audio/video content signal 14. In some examples, the audio signature processor 20 sequentially generates reference signatures or signature information for a series of audio/video content portions (e.g., audio/video programs) derived from the signal 14 and compares the reference signature information to the signature information ofthe audio/video content currently being consumed. If the comparison of reference signature information to the currently viewed audio/video content signature information yields a substantial match, the audio signature processor 20 identifies the audio/video content currently being consumed via the output device 12 as the audio/video content associated with the reference signature information to which the currently viewed audio/video content signature information substantially matched.

[0024] The audio signature processor 20 is coupled to a site unit 26. The audio signature processor 20 periodically or continuously sends consumption information (e.g., channel information, program information, audio/video content identification information, etc.) associated with audio/video content consumed via the output device 12 to the site unit 26. In turn, the site unit 26 processes the consumption information it receives from the audio signature processor 20 and sends, for example, viewing or consumption records to a central facility (not shown) via a communication link 28. The communication link 28 may include one or more wireless communication links (e.g., cellular, satellite, etc.), hardwired communication links (e.g., phone lines), or any other combination of communication hardware and technology platforms, communication protocols, etc.

[0025] While Fig. 1 depicts the audio signature processor 20 as being located at a consumption site, some or all ofthe functions ofthe audio signature processor 20 can be distributed among a plurality of physical locations. For instance, as discussed in greater detail in connection with the example system shown in Fig. 9 below, the reference signature generation function, the signature comparison function and/or the signature match detection function may be performed by different physical systems, some or all of which may be located in different physical locations. [0026] Additionally, although the example system 10 of Fig. 1 may be configured to receive and process audio/video content delivered via a broadcast signal (i.e., the signal 14), those having ordinary skill in the art will readily recognize that the example system 10 could be configured to alternatively or additionally receive and process audio/video content delivered via other manners. For example, local audio/video content delivery devices such as a DVD player, a DVR, a VCR, etc. may provide signals containing audio/video content consumed via the output device 12 to the audio signature processor 20. As with the audio/video content delivered via the signal 14, audio/video content delivered via one or more local sources could be processed by the audio signature processor 20 and/or the site unit 26 to generate audio/video consumption information.

[0027] Fig. 2 is a more detailed block diagram that depicts an example manner in which the audio signature processor 20 shown in Fig. 1 may be implemented. The example audio signature processor 120 shown in Fig. 2 includes an audio/video content selector 122 that receives a reference signal 121 (which may, for example, correspond to the signal 14) that contains audio/video content (e.g., a plurality of broadcast channels and programs) available for consumption (e.g., viewing, listening, etc.) and selects a particular portion of that audio/video content (e.g., a particular broadcast channel and/or program) for further processing. In particular, in the case where the reference signal 121 is a multi-program analog audio/video content signal, the audio/video content selector 122 may vary a demodulator mixing frequency to selectively tune to a particular channel. On the other hand, if the reference signal 121 is a multi-program digital audio/video data stream, the audio/video content selector 122 may include digital receiver functions that demodulate, demultiplex and selectively parse the data stream to extract audio data packets associated with a particular broadcast channel and/or audio/video program. In either case, the techniques for processing such multi-program analog signals and digital signals are well known and, thus, are not described in greater detail herein. [0028] In general, the audio/video content selection performed by the audio/video content selector 122 results in the sequential generation of signature information for a plurality of audio/video content portions (e.g., broadcast channels and programs). Also, generally, the audio/video content selection continues (i.e., selects different content portions such as, for example, different broadcast channels) until the audio signature processor 120 determines that a substantial match has been identified (i.e., that the audio/video currently being consumed via the output device 12 (Fig. 1) can be identified with a relatively high degree of certainty), or until the signature processor 120 determines that a substantial match cannot be identified (e.g., all available audio/video content portions have been selected, processed to form audio signatures and none of those audio signatures substantially matches the audio signature ofthe audio/video content currently being consumed). In one example, the selection process performed by the audio/video content selector 122 may be based on a predetermined numerical sequence. In another example, the selection process may be based on a probability of matching. For example, the audio/video content selector 122 may select those broadcast channels consumed most recently. Additionally or alternatively, the audio/video content selector 122 may select broadcast channels in a sequence based on their frequency of consumption.

[0029] The audio/video content selector 122 outputs a signal 124 to a signature generator 126. The signal 124 contains audio information derived from the audio/video content currently selected by the audio/video content selector 122. The signature generator 126 processes the audio information it receives to generate audio signature information therefrom. In particular, the signature generator 126 measures the magnitudes ofthe peak values ofthe signal 124 between successive zero crossings ofthe signal 124. As is well understood by those having ordinary skill in the art, a zero crossing is a point of zero signal magnitude between a positive signal magnitude and a negative signal magnitude. The sum ofthe magnitudes is then calculated for each of a plurality of time intervals or sample intervals. As a result, a series of such sums is generated. The resulting series of sums is substantially uniquely characteristic ofthe signal 124 and, thus, may be used as a reference audio signature for the audio/video content being provided to the signature generator 126 via the audio/video content selector 122.

[0030] Another signature generator 128 receives an audio output signal from the output device 12 (e.g., the audio signal 22 or, alternatively, the audio signal 25 from the acoustic transducer 24). The signature generator 128 is substantially the same as or identical to the signature generator 126 and, thus, generates audio signature information in a substantially similar or identical manner to that ofthe signature generator 126. As described in greater detail below in connection with Fig. 3, the signature generators 126 and 128 may each include a smoothing function that serves to eliminate noise, spurious data, etc. to facilitate the matching of signature information derived from the same audio/video content delivered via different signal paths (e.g., via an output device audio output and the reference signal). [0031] A time stamper 130 may optionally be coupled to one or both ofthe signature generators 126 and 128. The time stamper 130 may provide time stamps that are used by the signature generators 126 and 128 to time stamp signature data generated thereby. For example, each sum of peak values may have a time stamp associated therewith to facilitate subsequent signature comparison operations, correlation operations, matching operations, etc. In some examples, the time stamper 130 may generate relatively coarse time intervals such as, for example, one second increments, each of which may correspond to an absolute time or a relative time based on some reference time. However, as described in greater detail below, time stamps and thus, the time stamper 130, are not necessary to perform signature comparisons, correlations and the like.

[0032] The signature generators 126 and 128 provide respective signature information 132 and 134 to a signature comparator 136. The signature comparator 136 compares the audio signature information 132 associated with or generated from the audio/video content information (i.e., the signal 124) that is currently selected (i.e., selected by the audio/video content selector 122) from the reference signal 121 to the signature information 134, which is associated with or generated from the output device audio output signal (i.e., an audio signal or information associated with the audio/video content currently being consumed via the output device 12). In the case where the optional time stamper 130 is used, the signature comparator 136 may use time stamps associated with the signature data when performing signature matching activities, correlation activities, etc. In some examples, the time stamps may be used to approximately align or correlate data in different signature data records or files. Those having ordinary skill in the art will appreciate that such a rough or approximate alignment may significantly reduce the amount of time and/or processing needed to perform signature matching operations. [0033] The comparison of audio signatures can be performed using any known or desired technique. One preferred manner of comparing audio signatures, particularly in examples where the signature comparisons are performed locally (e.g., at each consumption site), uses the well-known standard normalized correlation formula. [0034] In one particular example, the signature comparator 136 compares signatures by calculating a sum of differences between the reference signature information 132 and the signature information associated with the audio/video content currently being consumed (i.e., the signature information 134) over a predetermined interval or time period. If the sum of differences is less than or equal to a predetermined threshold, the signature comparator 136 may provide an output signal or information 138 indicating that at least a substantial match has been detected (i.e., that the known audio/video content currently selected by the audio/video content selector 122 is substantially similar or identical to the audio/video content currently being consumed via the output device 12). Under this approach, threshold values may be selected to suit the requirements ofthe application. For example, relatively low threshold values may be used if a high degree of certainty in the audio/video content identification process is desired.

[0035] In another example, the signature comparator 136 may calculate a difference signal or error signal and then calculate an average error, a peak or maximum error, a standard deviation of error, or any other parameters characteristic ofthe differences, if any, between the signature information 132 and 134. One or more of those parameters or characteristics may be compared to one or more threshold values and a determination of whether a substantial' match or an identical match is indicated via the output 138 based on whether those parameters or characteristics are less than or greater than the one or more threshold values. [0036] The signature comparator 136 may also provide a feedback signal or information 140 to the audio/video content selector 122 to facilitate the sequential selection of audio/video content from the reference signal 121. For example in the event that the signature comparator 136 determines that the signature information 132 and 134 are not substantially similar or identical (i.e., the audio/video content currently selected or tuned from the reference signal 121 by the audio/video content selector 122 does not substantially match the audio/video content currently being consumed via the output device 12), the feedback signal 140 may indicate a non- match to the audio/video content selector 122. In turn, the audio/video content selector 122 may select or tune the next portion of audio/video content (e.g., a different broadcast channel and/or program) in its search or scan sequence. [0037] An audio/video content identifier 142 is coupled to the signature comparator 136 and receives the match information output 138. If the audio/video content identifier 142 receives information (via the output signal 138) indicating that a substantial or identical match has been identified, the audio/video content identifier 142 determines to what audio/video content portion (e.g., channel) the audio/video content selector 122 is tuned and, thus, can identify what audio/video content is currently being consumed via the output device 12. For example, in the case where the reference signal 121 is a broadcast audio/video signal, the audio/video content identifier 142 may be configured to determine, based on a program lineup or schedule, which channel and/or program is being consumed via the output device 12 (Fig. 1).

[0038] The audio/video content identifier 142 may be coupled to the site unit 26 (Fig. 1) to provide the identification information (e.g., broadcast channel, program identity, etc.) to the site unit 26 (Fig. 1). The site unit 26 can use the audio/video content identification information provided by the audio/video content identifier 142 to generate viewing records and the like. [0039] Fig. 3 is a more detailed block diagram that depicts an example manner in which the signature generators 126 and 128 shown in Fig. 2 may be implemented. The example signature generator 226 shown in Fig. 3 receives an input signal 228 (which may, for example, correspond to the signal 124 output by the audio/video selector 122) via signal conditioning circuitry 230. The signal conditioning circuitry 230 may include analog and or digital circuitry for filtering (e.g., noise filtering, anti- aliasing filtering, transient filtering, etc.). One particularly useful filtering circuit may provide a bandpass filter characteristic from 300 hertz to 3000 hertz. Additionally or alternatively, the signal conditioning circuitry 230 may include protection circuitry (e.g., surge protection circuitry), level shifting circuitry, amplification circuitry, attenuation circuitry, or any other known or desired signal conditioning circuitry. Of course, the signal conditioning circuitry 230 may be eliminated from the signature generator 226 in the event that the signals provided to the signature generator 226 do not require conditioning.

[0040] Conditioned signal(s) 232 output by the signal conditioning circuitry 230 are provided to a zero crossing detector 234 and a peak detector 236. The zero crossing detector 234 may use a one-shot multi-vibrator or the like to output a pulse to the peak detector 236 each time a zero crossing occurs within the conditioned signal(s) 232. The peak detector 236 may be implemented using any desired peak detection circuit to detect peak signal magnitude. For example, in the case where the signals 232 are analog signals, a diode, capacitor and bleed resistor combination may be used to detect peak value. On the other hand, in the case where the signals 232 are digital values, the peak detector 236 may simply retain the largest numerical value following a reset. The peak detector 236 resets (e.g., to zero) in response to zero crossing pulses or other signals provided by the zero crossing detector 234. As a result, the peak detector 236 outputs a series of signal peak magnitudes, each of which occurs between successive zero crossings. [0041] A summer 238 receives the series of peak signal magnitudes from the peak detector 236 and generates sums of these peak signal magnitudes for each ofthe predetermined time intervals or sample intervals. In one example, the summer 238 may sum a plurality of peak magnitudes (absolute values) occurring within a predetermined number of samples (e.g., 125 samples) collected at a predetermined rate (e.g., 8000 samples per second) from the conditioned signal 232. However, other sample sizes and sample rates may be used instead to suit the needs of a particular application. An output 242 ofthe summer 238 provides a series of positive sum values at a rate equal to the sample rate divided by the sample size for each sum. Thus, in the example where the sample rate is 8000 samples/second and the sample size per sum is 125, the output 242 provides sums at a rate of 64 per second. Additionally, as depicted in Fig. 3, the summer 238 may also receive a signal 240 (e.g., time stamp values) from the time stamper 130 (Fig. 2) that enables the summer 238 to associated time stamp values with one or more ofthe sums at the output 242. [0042] The signature generator 226 may also include a smoother 244 that performs a smoothing function on the series of sums output by the summer 238. For example, the smoother 244 may perform a low pass filter function to eliminate noise and other spurious interference or signal components that may adversely affect signature match detection. One particularly useful smoothing function may be based on the formula y(t) = a*x(t) + b*y(t-l), where y represents the smoothed data, x represents the sum data provided at the output 242, and a + b = 1. Preferably, a = b = 0.5. However, a and b may be different values if desired to suit the needs of a particular application. A smoothing function such as the example function set forth above may be successively applied to the data multiple times (e.g., ten times) to achieve a desired smoothness. [0043] The filtering performed by the smoother 244 may be implemented using any desired combination of passive components (i.e., resistors, capacitors, inductors, etc.), active components (i.e., transistors, operational amplifiers, etc.) and/or digital components (i.e., digital logic, processing units, memory, etc.). There are many well- known analog and numerical (i.e., digital) filtering techniques that may be used to implement the smoother 244 and, thus, such implementation details are not discussed in greater detail herein.

[0044] Fig. 4 is an example graph 300 that depicts an audio signal 302 that may be processed by the example signature generator 226 shown in Fig. 3. The signal 302 may be provided as the input 228 (Fig. 3) to the signal conditioning circuitry 230 (Fig. 3) that, in turn, provides a conditioned version (e.g., the conditioned signal 232) ofthe signal 302 to the zero crossing detector 234 and the peak detector 236. By way of example, at a time to the interval sum retained by the summer 238 is reset to zero. Then, at a first zero crossing 304, the zero crossing detector 234 (Fig. 3) outputs a pulse to the peak detector 236 (Fig. 3) that resets the peak value retained by the peak detector 236 to zero. Following the first zero crossing 304, the signal 302 increases in magnitude until it reaches a peak value "a." The peak detector 236 retains the peak value "a" while the signal 302 decreases between "a" and a second zero crossing 306. At the second zero crossing 306, the peak detector 236 outputs the magnitude ofthe peak value "a" to the summer 238 and then resets its retained peak value to zero. Following the second zero crossing 306, the signal 302 decreases in value until it reaches a negative peak "b," the absolute value of which is retained by the peak detector 236 as the signal 302 increases to zero at a third zero crossing 308. At the third zero crossing 308, the peak detector 236 outputs the magnitude of "b" to the summer 238 and the zero crossing detector 234 outputs a pulse that resets the retained peak value ofthe peak detector 236 to zero. This process continues for peaks "d," through "k" up to time a t_! (which may correspond to a predetermined time interval or sample interval including, for example, 125 samples), at which point the summer 238 output its retained sum to the smoother 244 (Fig. 3) and resets its retained sum to zero. The signature generator 126 repeats this process over the predetermined time interval, sample interval, or number of samples between times ti and t₂ for peaks "1" through "r," which results in a second sum being passed to the smoother 244. Of course, the process depicted graphically in Fig. 4 could be carried out for any desired number of intervals, which do not necessarily have to be immediately successive or contiguous. Further, in general, as the number of sums used to provide signature information for a particular audio signal increases, the certainty with which that signature uniquely identifies that particular audio signal increases. [0045] Fig. 5 is an example graph that depicts zero crossing data that may be generated by the example audio signature processor 120 of Fig. 2 from an audio signal such as, for example, the example signal 302 of Fig. 4. More specifically, the sequence of sums output by the summer 238 (e.g., the output 242), which may be generally referred to as a zero crossing energy curve, is depicted at reference numeral 320. Again, as noted above, in the case where the signal 302 is processed as a series of discrete data values, the zero crossing energy curve 320 has fewer discrete data values in any given time period or sample period because a plurality of samples or peak magnitude values from the signal 302 are summed to form each data value making up the zero crossing energy curve 320. In the case where 125 samples from the signal 302 are summed, a data reduction ratio of 125:1 (i.e., from the signal 302 to the zero crossing energy curve 320) is realized. However, as noted above, any other data reduction ratio may be used instead. The zero crossing energy curve 320 may then be processed by the smoother 244 to form a smoothed zero crossing energy curve 322. [0046] Fig. 6 is a block diagram that depicts another example manner in which the audio signature processor 20 shown in Fig. 1 may be implemented. The example audio signature processor 420 is a processor-based system that includes a processor 422 coupled to a memory 424 having software, firmware and/or any other machine readable instructions 425 stored therein. As described in greater detail in connection with Figs. 7 and 8 below, the processor 422 executes the software, firmware and/or machine readable instructions 425 to implement substantially the same signature generation, signature comparison and audio/content (e.g., channel, program, etc.) identification functions performed by the apparatus shown in Figs. 2 and 3. [0047] The processor 422 may be any suitable microprocessor, microcontroller or processing unit capable of executing machine readable instructions. The memory 424 may be an desired combination of volatile and non- volatile memory including, for example, read-only memory (ROM) devices, electrically erasable programmable read only memory (EEPROM) devices, random access memory (RAM) devices, mass storage devices (e.g., disk drives for magnetic or optical media), or any other suitable storage devices.

[0048] The example audio signature processor 420 may also include an audio/video content selector 426, which may be substantially similar or identical to the audio/video content selector 122 (Fig. 2) that receives a reference signal such as, for example, the signal 14 (Fig. 1). The audio/video content selector 426 is controlled by the processor 422 to scan or search a series of audio/video content portions (e.g., broadcast channels or programs) in a predetermined sequence. As described above in connection with the audio/video content selector 122, the audio/video content selection process or sequence may be based one or more factors such as, for example, the frequency with which audio/video content portions (e.g., channels) are typically consumed, the most recently consumed channels, etc. The audio/video content selector 426 outputs a signal 428 that contains audio information associated with a particular portion of audio/video content derived from the reference signal (e.g., a particular broadcast channel, program, etc.)

[0049] A signal conditioner 430 receives the signal 428 and the output device output signal 22 (Fig. 1). The signal conditioner 430 may be substantially the same or identical to the signal conditioning circuitry 230 (Fig. 3).

[0050] An analog-to-digital (A D) converter 432 receives the audio signals output by the signal conditioner 430. The A/D converter 432 includes at least two channels to enable the simultaneous analog-to-digital conversion ofthe conditioned versions of the reference signal 428 and the output device audio output.

[0051] The audio signature processor 420 also includes a communications interface 434 that enables the processor 422 to communicate with the site unit 26 (Fig.

1). For example, the communications interface 434 may include level shifting circuitry, bus line or signal line driver circuitry and/or any other known or desired communications circuitry.

[0052] Fig. 7 is a flow diagram that depicts an example manner in which the audio signature processor 420 shown in Fig. 6 may be configured to perform the audio signature processing functions described herein. Initially, the processor 422 (Fig. 6) controls the audio/video content selector 426 (Fig. 6) to select a known audio/video content (e.g., a broadcast channel or program) from the reference signal (block 500).

For example, the processor 422 (Fig. 6) may cause the audio/video content selector

426 (Fig. 6) to select or tune to the most frequently consumed channel, the last consumed channel, a channel in a predetermined sequence, etc. [0053] The processor 422 then controls the A/D converter 432 to acquire audio information or data associated with the selected audio/video content (via the signal 428 and the signal conditioner 430) and the output device audio output (block 502). Specifically, the processor 422 acquires digital values representing an audio reference signal (associated with known, selected audio/video content) and an audio signal associated with audio/video content currently being consumed via the output device 12 (Fig. 1). The processor 422 generates audio signatures or signature information from the acquired digital values (block 504) by summing peak signal magnitudes between successive zero crossings over a plurality of time intervals or sample intervals as described in greater detail in connection with Fig. 8. The processor 422 compares the audio signature information (block 506) and determines if the audio signature information associated with the selected audio/video content matches (i.e., is substantially similar or identical to) the audio signature information associated with the audio/video content (e.g., channel or program) currently being consumed via the output device 12 (Fig. 1) (block 508).

[0054] If a match is detected at block 508, the processor 422 (Fig. 6) identifies the audio/video content currently being consumed via the output device 12 as the audio/video content currently selected by the audio/video content selector 426 (Fig. 6) (block 510). Of course, the processor 422 (Fig. 6) may, if desired, also determine the program (e.g., a television program) that is associated with the identified audio/video content by using channel information (which may be known by the processor 422 as described below), local time information (i.e., the time at the consumption site 10) and program guide information (e.g., a television programming guide). In the case where the reference signal contains broadcast audio/video content, the processor 422 may be programmed to cause the audio/video content selector 426 to rune to one or more predetermined channels or programs and may associate channel or other tuning information (e.g., packet selection criteria in the case where the reference signal contains digital audio/video signals) with the signature information. [0055] On the other hand, if the processor 422 does not detect a match at block 508, the processor 422 determines if there are more audio/video content portions (e.g., channels) to be scanned or searched within the signal 14 (Fig. 1) (block 512). If there are more audio/video content portions to scan or search, the processor 422 (Fig. 6) selects another audio/video content portion (e.g., another channel) from the signal 14 (Fig. 1) (block 514). The selection of a next audio/video content portion (block 514) may be based on a determination of what audio/video content portions are more likely to be consumed via the output device 12 (Fig. 1), what audio/video content portions (e.g., channels) were most recently consumed, a predetermined sequence of audio/video content portions, or in any other desired manner. Once another audio/video content portion has been selected, control returns to block 502. If the processor 422 determines at block 512 that there are no more audio/video content portions to be selected (and there have been no matches at block 508), the processor 422 may execute error handling routines such as, for example, generating an error message that can be transmitted to the site unit 26 (Fig. 1) via the communications interface 434 (Fig. 6).

[0056] Fig. 8 is a flow diagram that depicts an example manner by which the audio signature processor 420 shown in Fig. 6 may be configured to perform the audio signature generation function described in connection with block 504 of Fig. 7. Initially, the processor 422 resets a sample interval sum to zero (block 600) and then waits for a zero crossing ofthe audio signal for which a signature is to be generated (e.g., the output device audio output signal and/or the signal 428) (block 602). Upon detection of a zero crossing (block 602), the processor 422 (Fig. 6) continuously or periodically acquires the peak magnitude ofthe signal (block 604) until a subsequent zero crossing is detected (block 606). After the subsequent zero crossing is detected (block 606), the processor 422 adds the peak magnitude acquired at block 604 to an interval sum (block 608). The processor 422 then determines if the sample interval has expired (e.g., a predetermined amount of time has elapsed, a predetermined number of samples have been acquired, etc.) (block 610). The sample interval may be a predetermined amount of time during which peak magnitudes are summed. If the sample interval has not expired (block 610), the processor 422 returns control to block 604. On the other hand, if the sample interval has expired, the processor 422 sends the current interval sum to a smoothing function (block 612) and then returns control to block 600.

[0057] The methods described in connection with Figs. 7 and 8 above may be especially useful when applied in a system that performs local (e.g., at each consumption site) audio/video content matching or correlation on a substantially real time basis. However, those having ordinary skill in the art will readily appreciate that the methods described in connection with Figs. 7 and 8 may be readily adapted for use in applications in which audio/video content matching or correlation is performed at a central facility and/or using historical (e.g., previously gathered) consumption records or information. [0058] Fig. 9 is another example manner in which the audio signature apparatus and methods described herein may be implemented. The example system 700 shown in Fig. 9 includes a broadcast station 702 that receives audio/video content from a plurality of content providers 704 and 706. The audio/video content providers 704 and 706 may provide audio and/or video programs or information such as for example, television programs, advertisements, audio (e.g., radio) programs, still image information (e.g., web pages), etc. in known manners to the broadcast station 702. The broadcast station 702 transmits one or more signals containing digital and/or analog audio/video content information to a reference site 708 and at least one consumption site 710 via communication paths or links 712 and 714. The communication paths or links 712 and 714 may include any combination of hardwired or wireless links such as, for example, satellite links, wireless land-based links, cable links, etc. The signals conveyed via the links 712 and 714 may contain multi-program analog signals and/or digital data streams, which are commonly employed with existing broadcast systems.

[0059] In the example system 700, the functions performed by the audio signature processor 20 shown in Fig. 1 are distributed between the reference site 708 and the consumption site 710. Specifically, the reference site 708 includes a plurality of receivers (e.g., set-top boxes or the like) 716, 718 and 720 that simultaneously demodulate, demultiplex and/or decode audio, video and/or other information received from the broadcast station 702. In one example, each ofthe receivers 716, 718 and 720 provides audio information associated with a different program that is currently being broadcast to a reference site processor 722. In other words, the receiver 716 may provide audio information associated with a program A while the receivers 718 and 720 provide audio information associated with respective programs B and C. In any case, the reference site processor 722 is configured to control and/or has information indicating to which program each ofthe receivers 716, 718 and 720 is currently tuned. [0060] The reference site processor 722 includes the apparatus and methods described herein for generating reference signature information for a plurality of simultaneously broadcast audio/video content. In particular, the reference site processor 722 may include one or more signature generators 226 shown and described in connection with Fig. 3. The reference site processor 722 sends the reference signature information it generates to a central processing facility 724, which stores the reference signature information in a database 726.

[0061] The consumption site 710 could be, for example, a statistically selected home containing a television, a radio, a computer, etc. The consumption site 710 includes an output device 728 (e.g., a video display, speaker, etc.) The consumption site 710 also includes a receiver (e.g., a set-top box) 730, which may be similar or identical to the receivers 716-720. Such receivers are well known and, thus, are not described in greater detail herein. The receiver 730 provides audio and/or video signals 732 to the output device 728 that are used to output the program currently selected for consumption. In addition, the receiver 730 also provides an audio signal 734 containing audio information associated with the currently consumed program to a consumption site processor 736. In turn, the consumption site processor 736 performs the signature generation functions described in connection with the signature generator 226 of Fig. 3 and sends the generated audio signature information to a site unit 738. The site unit 738 stores and periodically conveys the generated audio signature information to the central processing facility 724. [0062] The central processing facility 724, among other tasks, is configured to perform the functions ofthe audio signature comparator 136 and the audio/video content identifier 142 discussed in connection with Fig. 2. Thus, the central processing facility 724 compares signature information generated at the consumption site 710 to the reference signature information stored in the database 726 to identify the channels and/or programs consumed at the consumption site 710. To facilitate the comparison of audio signature information received from the reference site 708 to the audio signature information received from the consumption site 710, the reference site processor 722 and the consumption site processor 736 may generate time stamp information and associate such time stamp information with the audio signature information. For example, each interval sum may have an associated time stamp. In this manner, the central processing facility 724 can temporally align (at least approximately) the audio signature information received from the sites 708 and 710 prior to making comparisons.

[0063] Although certain example audio signature apparatus and methods have been described herein, the functional blocks making up these examples can be implemented using any desired combination of analog and/or digital hardware. Further, some or all of these functional blocks may be implemented within a processor-based system that executes machine readable instructions or programs, which may be embodied in software stored on a tangible medium such as a CD-ROM, a floppy disk, a hard drive, a DVD, or a memory. Still further, some or all ofthe functional blocks may be combined or integrated together and/or implemented using multiple functional blocks.

[0064] Although certain methods, apparatus and articles of manufacture have been described herein, the scope of coverage of this patent is not limited thereto. To the contrary, this patent covers all embodiments including apparatus, methods and articles of manufacture fairly falling within the scope ofthe appended claims, either literally or under the doctrine of equivalents.

Claims

What is claimed is:

1. A method of generating a signature for audio/video content, comprising: detecting a plurality of zero crossings of an audio signal associated with the audio/video content; acquiring a plurality of peak signal magnitudes, each of which occurs between successive ones ofthe plurality of zero crossings; summing ones ofthe peak signal magnitudes occurring within a first time interval to form a first sum; and generating the signature based on the first sum.

2. A method as defined in claim 1 , further comprising: summing ones ofthe peak signal magnitudes occurring within a second time interval to form a second sum; and generating the signature based on the first and second sums.

3. A method as defined in claim 2, wherein generating the signature based on the first and second sums includes smoothing the first and second sums.

4. A method as defined in claim 1, wherein the audio/video content includes at least one of a television program and an audio program.

5. A method as defined in claim 1 , wherein the successive ones ofthe plurality of zero crossings are temporally adjacent.

6. A method as defined in claim 1 , wherein the audio signal includes at least one of analog information and digital information.

7. An apparatus for generating a signature for audio/video content, comprising: a memory; and a processor coupled to the memory and programmed to: detect a plurality of zero crossings of an audio signal associated with the audio/video content; acquire a plurality of peak signal magnitudes, each of which occurs between successive ones ofthe plurality of zero crossings; sum ones ofthe peak signal magnitudes occurring within a first time interval to form a first sum; and generate the signature based on the first sum.

8. An apparatus as defined in claim 7, wherein the processor is further programmed to: sum ones ofthe peak signal magnitudes occurring within a second time interval to form a second sum; and generate the signature based on the first and second sums.

9. An apparatus as defined in claim 8, wherein the processor is programmed to smooth the first and second sums to generate the signature.

10. An apparatus as defined in claim 7, wherein the audio/video content includes at least one of a television program and an audio program.

11. An apparatus as defined in claim 7, wherein the successive ones ofthe plurality of zero crossings are temporally adjacent.

12. An apparatus as defined in claim 7, wherein the audio signal includes at least one of analog information and digital information.

13. A machine readable medium having instructions stored thereon that, when executed, cause a machine to: detect a plurality of zero crossings of an audio signal associated with

audio/video content; acquire a plurality of peak signal magnitudes, each of which occurs between successive ones ofthe plurality of zero crossings; sum ones ofthe peak signal magnitudes occurring within a first time interval to form a first sum; and generate the signature based on the first sum.

14. A machine readable medium as defined in claim 13 having instructions stored thereon that, when executed, cause the machine to: sum ones ofthe peak signal magnitudes occurring within a second time interval to form a second sum; and generate the signature based on the first and second sums.

15. A machine readable medium as defined in claim 14 having instructions stored thereon that, when executed, cause the machine to generate the signature based on the first and second sums by smoothing the first and second sums.

16. A method of generating a signature for audio/video content, comprising: detecting a zero crossing of an audio signal associated with the audio/video content; acquiring a peak signal magnitude ofthe audio signal subsequent to detecting the zero crossing; adding the peak signal magnitude to a sum of peak signal magnitudes; and generating the signature based on the sum of peak signal magnitudes.

17. A method as defined in claim 16, further comprising: detecting another zero crossing ofthe audio signal; acquiring another peak signal magnitude ofthe audio signal subsequent to detecting the other zero crossing; adding the other peak signal magnitude to another sum of peak signal magnitudes; and generating the signature based on the other sum of peak signal magnitudes.

18. A method as defined in claim 17, wherein generating the signature based on the other sum of peak signal magnitudes includes smoothing the other sum of peak signal magnitudes and the sum of peak signal magnitudes.

19. A method as defined in claim 17, wherein the zero crossings are temporally adjacent.

20. A method as defined in claim 16, wherein the audio/video content includes at least one of an audio program and a television program.

21. A method as defined in claim 16, wherein the audio signal includes at least one of analog and digital information.

22. An apparatus for generating a signature for audio/video content,

comprising: a memory; and a processor coupled to the memory and programmed to: detect a zero crossing of an audio signal associated with the audio/video content; acquire a peak signal magnitude ofthe audio signal subsequent to detecting the zero crossing; add the peak signal magnitude to a sum of peak signal magnitudes; and generate the signature based on the sum of peak signal magnitudes.

23. An apparatus as defined in claim 22, wherein the processor is further programmed to: detect another zero crossing ofthe audio signal; acquire another peak signal magnitude ofthe audio signal subsequent to detecting the other zero crossing; add the other peak signal magnitude to another sum of peak signal magnitudes; and generate the signature based on the other sum of peak signal magnitudes.

24. An apparatus as defined in claim 23, wherein the processor is programmed to generate the signature based on the other sum of peak signal magnitudes by smoothing the other sum of peak signal magnitudes and the sum of peak signal magnitudes.

25. An apparatus as defined in claim 23, wherein the zero crossings are temporally adjacent.

26. An apparatus as defined in claim 22, wherein the audio/video content includes at least one of an audio program and a television program.

27. An apparatus as defined in claim 22, wherein the audio signal includes at least one of analog and digital information.

28. A machine readable medium having instructions stored thereon that, when executed, cause a machine to: detect a zero crossing of an audio signal associated with audio/video content; acquire a peak signal magnitude ofthe audio signal subsequent to detecting the zero crossing; add the peak signal magnitude to a sum of peak signal magnitudes; and generate the signature based on the sum of peak signal magnitudes.

29. A machine accessible medium as defined in claim 28 having instructions stored thereon that, when executed, cause the machine to: detect another zero crossing ofthe audio signal; acquire another peak signal magnitude ofthe audio signal subsequent to detecting the other zero crossing; add the other peak signal magnitude to another sum of peak signal magnitudes; and generate the signature based on the other sum of peak signal magnitudes.

30. A machine accessible medium as defined in claim 29 having instructions stored thereon that, when executed, cause the machine to generate the signature based on the other sum of peak signal magnitudes by smoothing the other sum of peak signal magnitudes and the sum of peak signal magnitudes.

31. A method of generating a signature for audio/video content, comprising: detecting a plurality of zero crossings of an audio signal associated with the audio/video content; calculating sums of peak signal values for respective groups of zero crossings; and generating the signature for the broadcast program based on the sums of peak signal values.

32. A method as defined in claim 31 , wherein the respective groups of zero crossings correspond to respective time intervals ofthe audio signal.

33. A method as defined in claim 31 , wherein each of the peak signal values is a magnitude ofthe audio signal.

34. A method as defined in claim 31, wherein the audio signal includes at least one of analog information and digital information.

35. A method as defined in claim 31 , wherein the audio/video content includes at least one of an audio program and a television program.

36. A method as defined in claim 31 , wherein generating the signature for the audio/video content based on the sums of peak signal values includes smoothing the sums of peak signal values.

37. An apparatus for generating a signature for audio/video content,

comprising: a memory; and a processor coupled to the memory and programmed to: detect a plurality of zero crossings of an audio signal associated with the audio/video content; calculate sums of peak signal values for respective groups of zero crossings; and generate the signature for the broadcast program based on the sums of peak signal values.

38. An apparatus as defined in claim 37, wherein the respective groups of zero crossings correspond to respective time intervals ofthe audio signal.

39. An apparatus as defined in claim 37, wherein each ofthe peak signal values is a magnitude ofthe audio signal.

40. An apparatus as defined in claim 37, wherein the audio signal includes at least one of analog information and digital information.

41. An apparatus as defined in claim 37, wherein the audio/video content includes at least one of an audio program and a television program.

42. An apparatus as defined in claim 37, wherein the processor is programmed to generate the signature for the audio/video content based on the sums of peak signal values by smoothing the sums of peak signal values.

43. A machine accessible medium having instructions stored thereon that, when executed, cause a machine to: detect a plurality of zero crossings of an audio signal associated with audio/video content; calculate sums of peak signal values for respective groups of zero crossings; and generate the signature for the broadcast program based on the sums of peak signal values.

44. A machine accessible medium as defined in claim 43, wherein the respective groups of zero crossings correspond to respective time intervals ofthe audio signal.

45. A machine accessible medium as defined in claim 43, wherein each of the peak signal values is a magnitude ofthe audio signal.

46. A machine accessible medium as defined in claim 43, wherein the audio signal includes at least one of analog information and digital information.

47. A machine accessible medium as defined in claim 43, wherein the audio/video content includes at least one of an audio program and a television program.

48. A method of identifying a broadcast channel, comprising: receiving a broadcast signal at a consumption site; acquiring first audio information associated with the broadcast channel from an output device at the consumption site; summing a first group of peak signal magnitudes from the first audio information to generate first signature information; acquiring second audio information associated with a channel selected from the broadcast signal; summing a second group of peak signal magmtudes from the second audio information to generate second signature information; comparing the first and second signature information; and identifying the broadcast channel based on the comparison ofthe first and second signature information.

49. A method as defined in claim 48, further comprising determining the channel selected from the broadcast signal using a predetermined sequence of channels.

50. A method as defined in claim 49, wherein the predetermined sequence of channels is based on at least one of frequency of selection, time last consumed and probability of selection.

51. A method as defined in claim 48, wherein the each ofthe peak magnitudes within the first and second groups of peak signal magnitudes occurs between respective successive zero crossings.

52. A method as defined in claim 48, further comprising identifying a program consumed at the consumption site based on identification ofthe broadcast channel.

53. An apparatus for identifying a broadcast channel, comprising: a memory; and a processor coupled to the memory and programmed to: receive a broadcast signal at a consumption site; acquire first audio information associated with the broadcast channel from an output device at the consumption site; sum a first group of peak signal magnitudes from the first audio information to generate first signature information; ' acquire second audio information associated with a channel selected from the broadcast signal; sum a second group of peak signal magnitudes from the second audio information to generate second signature information; compare the first and second signature information; and identify the broadcast channel based on the comparison ofthe first and second signature information.

54. An apparatus as defined in claim 53, wherein the processor is further programmed to determine the channel selected from the broadcast signal using a predetermined sequence of channels.

55. An apparatus as defined in claim 54, wherein the predetermined sequence of channels is based on at least one of frequency of selection, time last consumed and probability of selection.

56. An apparatus as defined in claim 53, wherein the each ofthe peak magnitudes within the first and second groups of peak signal magnitudes occurs between respective successive zero crossings.

57. An apparatus as defined in claim 53, wherein the processor is programmed to identify a program consumed at the consumption site based on identification ofthe broadcast channel.

58. A machine readable medium having instructions stored thereon that, when executed, cause a machine to: receive a broadcast signal at a consumption site; acquire first audio information associated with a broadcast channel from an output device at the consumption site; sum a first group of peak signal magnitudes from the first audio information to generate first signature information; acquire second audio information associated with a channel selected from the broadcast signal; sum a second group of peak signal magnitudes from the second audio information to generate second signature information; compare the first and second signature information; and identify the broadcast channel based on the comparison ofthe first and second signature information.

59. A machine accessible medium as defined in claim 58 having instructions stored thereon that, when executed, cause the machine to determine the channel selected from the broadcast signal using a predetermined sequence of channels.

60. A machine accessible medium as defined in claim 59, wherein the predetermined sequence of channels is based on at least one of frequency of selection, time last consumed and probability of selection.

61. A machine accessible medium as defined in claim 58, wherein the each ofthe peak magmtudes within the first and second groups of peak signal magmtudes occurs between respective successive zero crossings.

62. A machine accessible medium as defined in claim 58 having instructions stored thereon that, when executed, cause the machine to identify a program consumed at the consumption site based on identification ofthe broadcast channel.

63. A method of identifying a broadcast channel, comprising: receiving a broadcast signal; generating signature information using sums of peak signal values derived from the broadcast signal; and identifying the broadcast channel based on the generated signature information.

64. A method as defined in claim 63, wherein the broadcast signal includes at least one of audio information and video information.

65. A method as defined in claim 63, wherein the broadcast signal includes at least one of analog information and digital information.

66. A method as defined in claim 63, wherein generating the signature information using the sums of peak signal values includes acquiring the peak signal values between zero crossings of an audio signal derived from the broadcast signal.

67. A method as defined in claim 63, wherein identifying the broadcast channel based on the generated signature information includes comparing portions of the generated signature information and identifying a match.

68. An apparatus for identifying a broadcast channel, comprising: a memory; and a processor coupled to the memory and programmed to: receive a broadcast signal; generate signature information using sums of peak signal values derived from the broadcast signal; and identify the broadcast channel based on the generated signature information.

69. An apparatus as defined in claim 68, wherein the broadcast signal includes at least one of audio information and video information.

70. An apparatus as defined in claim 68, wherein the broadcast signal includes at least one of analog information and digital information.

71. An apparatus as defined in claim 68, wherein the processor is programmed to generate the signature information using the sums of peak signal values by acquiring the peak signal values between zero crossings of an audio signal derived from the broadcast signal.

72. An apparatus as defined in claim 68, wherein the processor is programmed to identify the broadcast channel based on the generated signature information by comparing portions ofthe generated signature information and identifying a match.

73. A machine accessible medium having instructions stored thereon that, when executed, cause a machine to: receive a broadcast signal; generate signature information using sums of peak signal values derived from the broadcast signal; and identify the broadcast channel based on the generated signature information.

74. A machine accessible medium as defined in claim 73 having instructions stored thereon that, when executed, cause the machine to generate the signature information using the sums of peak signal values by acquiring the peak signal values between zero crossings of an audio signal derived from the broadcast signal.

75. A machine accessible medium as defined in claim 73 having instructions stored thereon that, when executed, cause the machine to identify the broadcast channel based on the generated signature information by comparing portions ofthe generated signature information and identifying a match.

76. A signature generator, comprising: a peak detector configured to receive an audio signal; a zero crossing detector configured to receive the audio signal and coupled to the peak detector to reset the peak detector in response to detection of a zero crossing ofthe audio signal; and a summer coupled to the peak detector and configured to sum peak signal values received from the peak detector.

77. A signature detector as defined in claim 76, further comprising a smoother coupled to the summer and configured to smooth a series of sums received from the summer.

78. A signature detector as defined in claim 76, wherein the audio signal is associated with at least one of a broadcast audio program and a broadcast television program.

79. A signature detector as defined in claim 76, wherein the audio signal includes at least one of analog information and digital information.

80. An audio signature detector, comprising: a first signature generator configured to receive a reference audio signal associated with a broadcast signal; and a second signature generator configured to receive an audio signal from a consumption site output device, wherein the first and second signature generators are configured to sum peak signal magnitudes from the reference audio signal and the audio signal from the consumption site output device over a plurality of time intervals to form first and second signatures.

81. An audio signature detector as defined in claim 80, further comprising a channel selector coupled to the first signature generator and configured to select the reference signal from a broadcast signal.

82. An audio signature detector as defined in claim 80, further comprising an audio signature comparator coupled to the first and second signature generators and configured to compare the first and second signatures.

83. An audio signature detector as defined in claim 82, further comprising a channel identifier coupled to the audio signature comparator and configured to receive a comparison output from the audio signature comparator and to identify at least one of a broadcast channel and a broadcast program based on the comparison output.

84. An audio signature detector as defined in claim 80, wherein the broadcast signal includes at least one of an audio program and a television program.

85. An audio signature detector as defined in claim 80, wherein the broadcast signal includes at least one of analog information and digital information.

86. An audio signature detector as defined in claim 80, wherein the first and second signature generators include respective first and second zero crossing detectors coupled to respective first and second peak detectors.

87. An audio signature detector as defined in claim 86, wherein the first and second zero crossing detectors are configured to reset their respective first and second peak detectors in response to detection of a zero crossing ofthe respective reference audio signal and the audio signal from the consumption site output device.