Search

Speech Synthesis by dyads concatenation produces an intelligible speech, but the lack of prosodic features like rythm and intonation gives the speech an unnatural and unpleasant sound. Having regard to the short-dated applied objectives, It's proving necessary to find a simple set of intonation patterns without taking the complexity of syntactic sentence structuration and the many derived rules into account. Intrinsic characteristics of each dyad are stored and a very simplified grammar is used to surimpose them automatically a pitch pattern, function of the following parameters: Type of sentences, End of each kind of syntagms, words boundaries, and words position inside a sentence.

The main features of the CNET diphone-based text-to-speech system for French language are described. The linguistic analysis works in three steps. First, a morphosyntactic analysis module assigns a grammatical value to each word in the text and transcribes it phonetically. A second module parses the text into hierarchical syntactico-prosodic groups. Finally, prosodic patterns are automatically assigned to each word by queries to a database of prosodic events. The phonetic and prosodic information serves as commands to the synthesis component. The synthesis component is based on diphone concatenation. A time-domain formulation of the pitch-synchronous overlap-add scheme (TD-PSOLA) is used to modify the speech prosody and to concatenate diphone waveforms. It is combined with a low bit-rate speech decoder to reduce the memory requirement for storing the diphone inventory. The system runs in real time on a PC equipped with a TMS320C25 DSP board and provides notably improved sound quality and naturalness in comparison to commercially available systems. >

Work done at CNET on developing multilingual concatenation-based PSOLA TTS (text-to-speech) systems well adapted to their use in interactive voice services is reviewed. A new system architecture SYC (synthesis control) has been specifically designed for assuring real-time, multichannel, and interactive operation. The data control and transfer methods within the system are now fully independent of the content of the modules, allowing for an easy adaptation of the system to multilingual operation. A complete version has been developed for German, and mixed systems have been elaborated for Italian and English in collaboration with other laboratories, using the same PSOLA synthesizer as for French. The overall quality of the French version has been improved both in naturalness (optimization of the linguistico-prosodic processings) and in articulation accuracy (use of longer units to be concatenated). An automatic segmentation procedure has been developed for the rapid building of new repertories of speech from recordings by new speakers, i.e., for the creation of new synthetic voices. >