Abstract
Abstract : We report on research toward a very-low-rate vocoder. This quarter we continued investigation in three areas. The first area of research is multi- speaker synthesis: speech synthesis from the transmitted vocoder parameters with the voice quality of the vocoder user. This processing entails speaker-specific spectral transformation of the vocoder diphone database. The second area of research is to improve the accuracy of the phonetic recognition. Our work this quarter concentrated on training the recognizer by augmentation of the diphone database with diphones extracted from natural, continuous speech. The third area of research is the development of an efficient model of continuous speech. We have developed a novel method of a variable-order Markov chain. We are continuing evaluation of this method.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
