The present invention pertains to a concatenative speech synthesis system and method which produces a more natural sounding speech. The system provides for multiple instances of each acoustic unit which can be used to generate a speech waveform representing an linguistic expression. The multiple instances...http://www.google.fr/patents/US5913193?utm_source=gb-gplus-shareBrevet US5913193 - Method and system of runtime acoustic unit selection for speech synthesis
Method and system of runtime acoustic unit selection for speech synthesis
