Czech HMM-Based Speech Synthesis: Experiments with Model Adaptation

Abstract

This paper describes some experiments on model adaptation for statistical parametric speech synthesis for the Czech language. For building an experimental TTS system, HTS toolkit was utilised. Speech was represented by using high-quality analysis/synthesis system STRAIGHT. For definition of speech unit context, a new reduced set of contextual factors was proposed. During model clustering, some missing contextual factors, that were not included in this set, can be simulated by using combined context-related clustering questions. The model transformation was performed by a combination of CMLLR and MAP adaptation. Speech data from 3 male and 3 female speakers was used in our experiments. In the performed listening test, speech generated from regularly trained and adapted models was compared. Both voices were evaluated as identical and of a similar quality.

This work was supported by the Grant Agency of the Czech Republic, project No. GAČR 102/09/0989 and by the Technology Agency of the Czech Republic, project No. TA01011264. Author would also like to thank Prof. Hideki Kawahara from Wakayama University for his permission to use the STRAIGHT analysis/synthesis method [5]. The access to the MetaCentrum computing facilities, provided under the programme “Projects of Large Infrastructure for Research, Development, and Innovations” LM2010005 funded by the Ministry of Education, Youth, and Sports of the Czech Republic, is appreciated.