Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 1759-1762

  Oura, Keiichiro ^a   Zen, Heiga ^a   Nankaku, Yoshihiko ^a   Lee, Akinobu ^a   Tokuda, Keiichi ^a  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Context clustering; Decision tree; Embedded device; HMM; MDL criterion; Speech synthesis

Indexed keywords

CLUSTERING TECHNIQUES; COVARIANCE MATRICES; EMBEDDED DEVICE; EMPIRICAL KNOWLEDGE; HMM; HMM-BASED SPEECH SYNTHESIS; MDL CRITERION; MEAN VECTOR; SPEECH WAVEFORMS; SUBJECTIVE LISTENING TEST; SYNTHESIZED SPEECH;

COVARIANCE MATRIX; DECISION TREES; HIDDEN MARKOV MODELS; SPEECH SYNTHESIS; SYNTHESIS (CHEMICAL);

SPEECH COMMUNICATION;

EID: 70450172128     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. A. W. Black and P. Taylor, "CHATR: a generic speech synthesis system," in Proc. COLING94, 1994.
2. A. Hunt and A. W. Black, "Unit selection in a concatenative speech synthesis system using a large speech database," in Proc. ICASSP, 1996, pp. 373-376.
3. R. E. Donovan and P. C. Woodland, "Automatic speech synthesizer parameter estimation using HMMs," in Proc. ICASSP, 1995, pp. 640-643.
4. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," Proc. Eurospeech, pp.2347-2350, 1999.
5. K. F. Lee, "Context-Dependent Phonetic Hidden Markov models for Speaker-Independent Continuous Speech Recognition," IEEE Trans. Acoustic Speech and Signal Processing, vol. 38, no. 4, pp. 599-609, 1990.
6. J. Takami and S. Sagayama, "A Successive State Splitting Algorithm for Efficient Allophone Modeling," Proc. ICASSP'92, pp. 573-576, 1992.
7. P. Woodland and S. Young, "Benchmark DARPA RM results with the HTK portable HMM toolkit," Proc. DARPA Continuous Speech Recognition Workshop, pp. 71-76, 1992.
8. M. Y. Hwang, X. Huang, and F. Alleva, "Predicting Unseen Triphones with Senones," Proc. ICASSP'93, pp .311-314, 1993.
9. M. Ostendorf and H .Singer, "HMM topology design using maximum likelihood successive state splitting," Computer Speech Language, vol. 1, no. 1, pp. 17-41, 1997.
10. J. J. Odell, "The Use of Context in Large Vocabulary Speech Recognition, PhD dissertation," Cambridge University, 1995.
11. K. Shinoda and T. Watanabe, "MDL-based Context-Dependent Subword Modeling for Speech Recognition," J. Acoust. Soc. Jpn.(E), vol .21, no. 2, pp. 79-8-6, 2000.
12. W. Chou and W. Reichl, "Decision Tree State Tying based on Penalized Bayesain Information Criterion," Proc. ICASSP'99, pp. 345-348, 1999.
13. S.Watanabe, Y. Minami, A. Nakamura, and N.Ueda, "Training of Shared States in Hidden Markov Model Based on Bayesian Approach" IEICE technical report. Speech, vol. 102, no. 35, pp. 43-48, 2002.
14. T. Kato, S. Kuroiwa, T. Shimizu, and N. Higuchi, "Tree-based Clustering for Gaussian Mixture HMMs," IEICE Trans. vol. J83-D-II, no. 11, pp. 2128-2136, 2000.
15. H. J. Nock, "Context Clustering for Triphone-based Speech Recognition," Master Thesis, Cambridge University, 1996.
16. A. Kuramatsu, K. Takeda, Y. Sagisaka, S. Katagiri, H .Kawabara, and K. Shikano, "ATR Japanese speech database as a tool of speech recognition and synthesis," Speech Communication, vol. 9, pp. 357-363, 1990.
17. K. Tokuda, T. Kobayashi, T. Chiba, and S. Imai, "Spectral Estimation of Speech by Mel-Generalized Cepstral Analysis," IEICE Trans. vol. 75-A, no. 7, pp. 1124-1134, 1992.
18. H. Kawahara, M. K. Ikuyo, A. Cheneigne, "Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds," Speech Communication, 27, pp. 187-207, 1999.
19. H. Zen, T. Masuko, K. Tokuda, T. Kobayashi, T. Kitamura, "A Hidden Semi-Markov Model-Based Speech Synthesis System," IEICE Trans. Inf. & Sys., vol. 90D, no. 5, pp. 825-834, 2007.
20. T. Toda, K. Tokuda, "Speech parameter generation algorithm considering global variance for HMM-based speech synthesis," Inter-speech 2005, pp. 2801-2804, 2005.
21. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Transactions on Speech and Audio Processing, vol. 7, no. 3, pp. 272-281, 1999.