A fully consistent hidden semi-markov model-based speech recognition system

IEICE Transactions on Information and Systems

Volumn E91-D, Issue 11, 2008, Pages 2693-2700

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

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Hidden Markov model; Hidden semi Markov model; Speech recognition; Weighted finite state transducer

Indexed keywords

APPROXIMATION ALGORITHMS; CONTINUOUS SPEECH RECOGNITION; DEEP NEURAL NETWORKS; HIDDEN MARKOV MODELS; MARKOV PROCESSES; PROBABILITY DISTRIBUTIONS; SPEECH; SPEECH PROCESSING; TRANSDUCERS; TRANSLATION (LANGUAGES);

CONTEXT-DEPENDENT DURATION MODELING; GENERALIZED FORWARD-BACKWARD; HIDDEN SEMI-MARKOV MODELING; HIDDEN SEMI-MARKOV MODELS; SPEAKER DEPENDENTS; SPEECH RECOGNITION SYSTEMS; TEMPORAL STRUCTURES; WEIGHTED FINITE-STATE TRANSDUCERS;

SPEECH RECOGNITION;

EID: 68749108220     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e91-d.11.2693     Document Type: Article

References (16)

1. M. Ostendorf, V. Digalakis, and O. Kimball, "From HMMs to segment models," IEEE Trans. Speech Audio Process., vol.4, no.5, pp.360-378, 1996.
2. S.E. Levinson, "Continuously variable duration hidden Markov models for automatic speech recognition," Comput. Speech Lang., vol.1, pp.29-45, 1986.
3. H. Zen, K. Tokuda, T. Masuko, and T. Kitamura, "A hidden semi-Markov model-based speech synthesis system," IEICE Trans. Inf. & Syst., vol.E90-D, no.5, pp.825-834, May 2007.
4. J. Ferguson, "Variable duration models for speech," Proc. Symposium on the Application of Hidden Markov Models to Text and Speech, pp.143-179, 1980.
5. Y. Ishimatsu, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Investigation of state duration model based gamma distribution for HMM-based speech synthesis," IEICE Technical Report, vol.101, no.352, pp.57-62, 2001.
6. M.J. Russell and A.E. Cook, "Experimental evaluation of duration modeling techniques for automatic speech recognition," Proc. ICASSP1987, vol.1, pp.2376-2379, 1987.
7. M. Wan. Koo, S.J. Park, and D.Y. Son, "Context dependent phoneme duration modeling with tree-based state tying," Proc. INTERSPEECH2004, vol.1, pp.721-724, 2004.
8. V.R.R. Gadde, "Modeling word duration," Proc. ICSLP2000, vol.1, pp.601-604, 2000.
9. 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, vol.5, pp.2347-2350, 1999.
10. J. Odell, The use of context in large vocabulary speech recognition, Ph.D. Thesis, Cambridge University, 1995.
11. K.F. Lee, "Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition," IEEE Trans. Acoust. Speech Signal Process., vol.38, no.4, pp.599-609, 1990.
12. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Proc. ASR2000, pp.97-106, 2000.
13. C. Allauzen and M. Mohri, "Generalized optimization algorithm for speech recognition transducers," Proc. ICASSP2003, vol.1, pp.352-355, 2003.
14. K. Shinoda and T. Watanabe, "Acoustic modeling based on the MDL criterion for speech recognition," Proc. EUROSPEECH, vol.1, pp.99-102, 1997.
15. S.Z. Yu and H. Kobayashi, "An efficient forward-backward algorithm for an explicit-duration hidden Markov model," IEEE Signal Process. Lett., vol.10, no.1, pp.11-14, 2003.
16. S. Nakagawa and H. Takagi, "Statistical methods for comparing pattern recognition algorithms and comments on evaluating speech recognition performance," J. Acoust. Soc. Jpn., vol.50, no.10, pp.849-854, 1994.