Multi-space probability distribution HMM

IEICE Transactions on Information and Systems

Volumn E85-D, Issue 3, 2002, Pages 455-464

  Tokuda, Keiichi ^a   Masuko, Takashi ^b   Miyazaki, Noboru ^b,c   Kobayashi, Takao ^b  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

^b TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^c NTT Communication Science Laboratories   (Japan)

Author keywords

FO; Hidden Markov model; Multispace probability distribution; Text to speech

Indexed keywords

ALGORITHMS; MATHEMATICAL MODELS; PARAMETER ESTIMATION; PATTERN RECOGNITION SYSTEMS; PROBABILITY DISTRIBUTIONS; SPEECH ANALYSIS; SPEECH RECOGNITION; SPEECH SYNTHESIS; STATISTICAL METHODS; VECTORS;

HIDDEN MARKOV MODEL; MULTISPACE PROBABILITY DISTRIBUTION; SPEECH SPECTRA;

MARKOV PROCESSES;

EID: 0036522887     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (16)

1. S. Schwartz, Y-L. Chow, O. Kimball, S. Roucos, M. Krasner, and J. Makhoul. "Context-dependent modeling for acoustic-phonetic of continuous speech," Proc. ICASSP85, pp. 1205-1208, March 1985.
2. S. Furui, "Speaker independent isolated word recognition using dynamic features of speech spectrum," IEEE Trans. Acoust., Speech & Signal Process., vol. 34, no. 1, pp. 52-59, Feb. 1986.
3. B.-H. Juang, "Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains," AT&T Technical Journal, vol. 64, no. 6, pp. 1235-1249, 1985.
4. J.J. Odell, "The use of context in large vocabulary speech recognition," PhD Thesis, Cambridge University, March 1995.
5. C.-H. Lee, C.-H. Lin, and B.H. Juang, "A study on speaker adaptation of the parameters of continuous density hidden Markov models," IEEE Trans. Acoust., Speech & Signal Process., vol. 39, no. 4, pp. 806-814, April 1992.
6. G.J. Freij and F. Fallside, "Lexical stress recognition using hidden Markov models," Proc. ICASSP88, pp. 135-138, April 1988.
7. U. Jensen, R.K. Moore, P. Dalsgaard, and B. Lindberg, "Modeling intonation contours at the phrase level using continuous density hidden Markov models," Computer Speech and Language, vol.8, no.3, pp. 247-260, July 1994.
8. 0 for synthesis," Proc. ESCA/IEEE Workshop on Speech Synthesis, pp. 131-134, Sept. 1994.
9. L.A. Liporace, "Maximum likelihood estimation for multivariate observations of Markov sources," IEEE Trans. Inf. Theory, vol. 28, no. 5, pp. 729-734, Sept. 1982.
10. M. Nishimura and K. Toshioka, "HMM-based speech recognition using multi-dimensional multi-labeling," Proc. ICASSP87, pp. 1163-1166, May 1987.
11. D. Xu, C. Fancourt, and C. Wang, "Multi-channel HMM," Proc. ICASSP96, pp. 841-844, May 1996.
12. N. Miyazaki, K. Tokuda, T. Masuko, and T. Kobayashi, "A study on pitch pattern generation using HMMs based on multi-space probability distributions," IEICE Technical Report, SP98-12, 1998.
13. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMM-based speech synthesis," ICASSP2000, pp. 1315-1318, June 2000.
14. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," Proc. EUROSPEECH99, pp. 2347-2350, Sept. 1999.
15. T. Masuko, K. Tokuda, T. Kobayashi, and S. Imai, "Speech synthesis from HMMs using dynamic features," Proc. ICASSP96, pp. 389-392, May 1996.
16. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Duration modeling for HMM-based speech synthesis," Proc. ICSLP98, pp. 29-32, Nov.-Dec. 1998.