New techniques for the compression of synthesizer databases

Author

Van der Vrecken, Olivier ; Pierret, N. ; Dutoit, Thzerry ; Pagel, V. ; Malfrere, F.

Author_Institution

Lab. de Theorie des Circuits et de Traitement du Signal, Fac. Polytech. de Mons, Belgium

Volume

4

fYear

1997

fDate

9-12 Jun 1997

Firstpage

2641

Abstract

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 implies the storage of a high number of segments. To facilitate the storage of these segments, this paper proposes a very low complexity coder to compress these databases with a toll quality. A particular interest has been taken in the databases of the MBROLA synthesizer constituted of fixed size frames. The developed coder uses this special characteristic to reach compression rates from 7 to 9 without degradation of the speech quality produced by the synthesizer

Keywords

data compression; speech coding; speech synthesis; MBROLA synthesizer; TTS synthesizers; compression rates; fixed size frames; segment storage; speech production; synthesis by concatenation; synthesizer database compression; toll quality; very low complexity coder; Circuit synthesis; Context modeling; Databases; Degradation; Signal synthesis; Smoothing methods; Speech coding; Speech synthesis; Steady-state; Synthesizers;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on

Print_ISBN

0-7803-3583-X

Type

conf

DOI

10.1109/ISCAS.1997.612867

Filename

612867