7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Eigenvoices for HMM-Based Speech Synthesis

Kengo Shichiri (1), Atsushi Sawabe (1), Takayoshi Yoshimura (1), Keiichi Tokuda (1), Takashi Masuko (2), Takao Kobayashi (2), Tadashi Kitamura (1)

(1) Nagoya Institute of Technology, Japan; (2) Tokyo Institute of Technology, Japan

This paper describes an eigenvoice technique for an HMM-based speech synthesis system which can synthesize speech with various voice qualities. In the eigenvoice technique, which has successfully been applied to fast speaker adaptation in an HMM based speech recognition, a large number of speaker dependent HMM sets are represented by a few parameters through a dimensionality reduction technique, e.g., PCA. In this paper, we propose an eigenvoice technique for speech synthesis, and apply it to an HMM-based speech synthesis system in which spectrum and F0 are modeled by HMMs, and synthetic speech generated fromHMMs themselves. The generated spectrum and F0 pattern are shown, and the relation between weights for eigenvoices and voice quality is discussed.


Full Paper

Bibliographic reference.  Shichiri, Kengo / Sawabe, Atsushi / Yoshimura, Takayoshi / Tokuda, Keiichi / Masuko, Takashi / Kobayashi, Takao / Kitamura, Tadashi (2002): "Eigenvoices for HMM-based speech synthesis", In ICSLP-2002, 1269-1272.