EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Variable-Length Acoustic Units Inference for Text-To-Speech Synthesis

Olivier Boeffard

IRISA, Université Rennes 1, ENSSAT, France

The best voices in text-to-speech synthesis are currently obtained via acoustic units concatenation-based systems. In such systems, the choice of units whose concatenations will produce an acoustic message is a crucial stage. Moreover, it can be observed that current TTS systems use acoustic units which most often correspond to variable-length phonetic descriptions. In this article, an original framework is proposed which allows the automatic determination of an optimum set of variable-length acoustic units.

Full Paper

Bibliographic reference.  Boeffard, Olivier (2001): "Variable-length acoustic units inference for text-to-speech synthesis", In EUROSPEECH-2001, 983-986.