431246

Adaptive Training for Hidden Semi-Markov Model

Yamagishi, Junichi ; Kobayashi, Takao

Interdisciplinary Graduate Sch. of Sci. & Eng., Tokyo Inst. of Technol., Japan

1

2005

March 18-23, 2005

365

368

hidden Markov models; maximum likelihood estimation; regression analysis; speech intelligibility; speech synthesis; HSMM adaptive training technique; MLLR adaptation; acoustic variability normalization; canonical model state duration distributions; hidden semi-Markov models; maximum likelihood linear regression; speaker difference normalization; speaker independent training; speech synthesis system; synthesized speech intelligibility; synthesized speech naturalness; Acoustical engineering; Adaptation model; Databases; Hidden Markov models; Loudspeakers; Maximum likelihood linear regression; Power system modeling; Probability distribution; Speech synthesis; System testing;

English

ieee

Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on

1520-6149

0-7803-8874-7

conf

10.1109/ICASSP.2005.1415126

1415126