5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Speaker Interpolation in HMM-Based Speech Synthesis System

Takayoshi Yoshimura (1), Takashi Masuko (2), Keiichi Tokuda (1), Takao Kobayashi (2), Tadashi Kitamura (1)

(1) Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan (2) Precision and Intelligence Laboratory, Tokyo Institute of Technology, Yokohama, Japan

This paper describes an approach tovoice characteristics conversion for HMM-based text-to-speech synthesis system using speaker interpolation. An HMM interpolation technique is derived from a probabilistic distance measure for HMMs, and used to synthesize speech with untrained speaker's characteristics by interpolating HMM parameters among some representative speakers' HMM sets. The results of subjective experiments show that we can gradually change the characteristics of synthesized speech from one's to the other's by changing the interpolation ratio.

Full Paper
Acoustic Examples:   #1   #2   #3   #4   #5  

Bibliographic reference.  Yoshimura, Takayoshi / Masuko, Takashi / Tokuda, Keiichi / Kobayashi, Takao / Kitamura, Tadashi (1997): "Speaker interpolation in HMM-based speech synthesis system", In EUROSPEECH-1997, 2523-2526.