Gerard Benbassat

Speech encoding process combining written and spoken message codes

A speech encoding process, wherein a first sequence of input data representative of a written version of a message to be coded is encoded to provide a first encoded speech sequence corresponding to the written version of the message to be coded, and a second sequence of input data derived from speech defining a spoken version of the same message is analyzed by a linear predictive codeing analyzer and encoding circuit to provide a second encoded speech sequence corresponding to the spoken version of the message to be coded. The codes of the corresponding written message and the codes of the spoken message are then combined in a control circuit encompassing an adaptation algorithm, and a composite encoded speech sequence is generated corresponding to the message from the combination of the first encoded speech sequence of the written version of the message and encoded intonation parameters of speech included in a portion of the second encoded speech sequence corresponding to the spoken version of the message. In a particular aspect of the speech encoding process, the encoded intonation parameters of speech included in the portion of the second encoded speech sequence corresponding to the spoken version of the message to be coded may be encoded data of the duration and pitch as the portion of the second encoded speech sequence combined with the first encoded speech sequence.

Low bit rate speech coding by concatenation of sound units and prosody coding

The purpose of this work was to develop a speech coding system working at a very low bit rate (100 bits/s) and capable of reproducing natural sounding speech. The approach chosen was to use a concatenation of small sound segments to assemble a sentence along with duration and pitch contour extracted (by Dynamic Time Warping) from a natural utterance of the same sentence. The segmental aspect is coded at the phonological level, thus leading to a bit rate around 60 bits/s. The decoding of the phonemes is obtained by a set of rules operating on phonetic features. The prosodic aspect is coded using stored pitch contours and duration patterns, thus leading to a bit rate around 40 b/s.

Application de la distinction trait-indice-propriete a la construction d'un logiciel pour la synthese

Abstract Synthesis by concatenation of speech segments is still a difficult problem concerning the choice of the size, the nature of the segments and the ‘quality’ performance, of the sound dictionary. In order to set up a methodical way of obtaining the best compromise, one must think in terms of the relationship between features, cues and physical properties. The decomposition of an allophone in sub-segments as well as their choice are obtained through a set of context dependent rules operating on features, cues and properties. The software integrates the tuning of these rules with the actual building and testing of the sound dictionary. A minimum of interaction between the writing of a rule and its testing is required from the operator. The operator is also given the possibility to extract automatically the sound segments from a vast corpus, using controls given in phonetic terms.