Sixth ISCA Workshop on Speech Synthesis

Bonn, Germany
August 22-24, 2007

Adaptive Database Reduction for Domain Specific Speech Synthesis

Aleksandra Krul (1), Géraldine Damnati (1), François Yvon (2), Cédric Boidin (1), Thierry Moudenc (1)

(1) France Télécom R&D Division, TECH/SSTP, Lannion, France
(2) GET/ENST and CNRS/LTCI, Paris, France

This paper raises the issue of speech database reduction adapted to a specific domain for Text-To-Speech (TTS) synthesis application. We evaluate several methods: a database pruning technique based on the statistical behaviour of the unit selection algorithm and a novel method based on the Kullback- Leibler divergence. The aim of the former method is to eliminate the least selected units during the synthesis of a domain specific training corpus. The aim of the latter approach is to build a reduced database whose unit distribution approximates a given target distribution. We compare the reduced databases. Finally we evaluate these methods on several objective measures given by the unit selection algorithm.

Full Paper

Bibliographic reference.  Krul, Aleksandra / Damnati, Géraldine / Yvon, François / Boidin, Cédric / Moudenc, Thierry (2007): "Adaptive database reduction for domain specific speech synthesis", In SSW6-2007, 217-222.