MLLR adaptation for hidden semi-Markov model based speech synthesis

@inproceedings{Yamagishi2004MLLRAF,
  title={MLLR adaptation for hidden semi-Markov model based speech synthesis},
  author={Junichi Yamagishi and Takashi Masuko and Takao Kobayashi},
  booktitle={INTERSPEECH},
  year={2004}
}
This paper describes an extension of maximum likelihood linear regression (MLLR) to hidden semi-Markov model (HSMM) and presents an adaptation technique of phoneme/state duration for an HMM-based speech synthesis system using HSMMs. The HSMM-based MLLR technique can realize the simultaneous adaptation of output distributions and state duration distributions. We focus on describing mathematical aspect of the technique and derive an algorithm of MLLR adaptation for HSMMs. 

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 11 extracted citations

Text-to-Speech Synthesis

View 20 Excerpts
Highly Influenced

A Speaker Adaptation Technique for MRHSMM-Based Style Control of Synthetic Speech

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 • 2007
View 2 Excerpts

Adaptive training for hidden semi-Markov model [speech synthesis applications]

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. • 2005
View 3 Excerpts

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Continuously variable duration hidden Markov models for automatic speech recognition

S. E. Levinson
Computer Speech and Language, vol.1, no.1, pp.29–45, 1986. • 1986
View 2 Excerpts

Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition

ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing • 1985
View 2 Excerpts

Variable duration models for speech

J. D. Ferguson
Symp. on the Application of Hidden Markov Models to Text and Speech, pp.143–179, 1980. • 1980
View 2 Excerpts

Similar Papers

Loading similar papers…