A Prosodic Model for Text-to-speech Synthesis in French

Text-to-speech synthesis, so long confined to small industrial applications, is now being opened up to many new areas of general interest, especially since the tremendous upsurge of multimedia applications. Endowing speech synthesis with the kind of quality that makes it acceptable and attractive to the general public is thus one of the major challenges of today’s speech technology research. A second challenge is the capability of processing unrestricted running texts, regardless of their length or content.