5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

A Simple and Efficient Algorithm for the Compression of MBROLA Segment Databases

Olivier van der Vrecken, Nicolas Pierret, Thierry Dutoit, Vincent Pagel, Fabrice Malfrere

Laboratoire de Theorie des Circuits et de Traitement du Signal (TCTS), Faculté Polytechnique de Mons, Belgium

Most state-of-the-art TTS synthesizers are based on a technique known as synthesis by concatenation, in which speech is produced by concatenating elementary speech units. The design of a high-quality TTS system implies the storage of a large number of segments. To facilitate the storage of these segments, this paper proposes a very low complexity coder to compress unit databases with a toll quality. A particular interest has been taken in the databases used by the MBROLA synthesizer, composed of fixed-length pitch periods with constrained harmonic phases. The coder developed here uses this special characteristic to reach compression rates from 7 to 9 without degrading the speech quality produced by the synthesizer, and with very limited computational cost.

Full Paper

Bibliographic reference.  Vrecken, Olivier van der / Pierret, Nicolas / Dutoit, Thierry / Pagel, Vincent / Malfrere, Fabrice (1997): "A simple and efficient algorithm for the compression of MBROLA segment databases", In EUROSPEECH-1997, 421-424.