Sixth ISCA Workshop on Speech Synthesis
Intonation synthesis using a hand-controlled interface is a new approach for effective synthesis of expressive prosody. A system for prosodic real time modification is described. The user is controlling prosody in real time by drawing contours on a graphic tablet while listening to the modified speech. This system, a pen controlled speech instrument, can be applied to text to speech synthesis along two lines. A first application is synthetic speech post-processing. The synthetic speech produced by a TTS system can be very effectively tuned by hands for expressive synthesis. A second application is database enrichment. Several prosodic styles can be applied to the sentences in the database without the need of recording new sentences. These two applications are sketched in the paper.
Full Paper Video (DivX, 62 MB)
Bibliographic reference. Beux, Sylvain Le / Rilliard, Albert / d’Alessandro, Christophe (2007): "Calliphony: a real-time intonation controller for expressive speech synthesis", In SSW6-2007, 345-350.