Efficient speech recognition using subvector quantization and discrete-mixture HMMS

Computer Speech and Language

Volumn 14, Issue 1, 2000, Pages 33-46

  Digalakis, V ^a   Tsakalidis, S ^a   Harizakis, C ^a   Neumeyer, L ^b  

^a TECHNICAL UNIVERSITY OF CRETE   (Greece)

^b SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; DECODING; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS; TABLE LOOKUP; VECTOR QUANTIZATION;

DISCRETE MIXTURE HIDDEN MARKOV MODELS; PRODUCT CODE VECTOR QUANTIZATION; SUBVECTOR QUANTIZATION;

SPEECH RECOGNITION;

EID: 0033899916     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1999.0134     Document Type: Article

References (13)

1. Bei, C. D. & Gray, R. M. (1985). An improvement of the minimum distortion encoding algorithm for vector quantization. IEEE Transactions on Communications, 33, 1132-1133.
2. Bocchieri, E. (1993). Vector quantization for the efficient computation of continuous density likelihoods. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Minneapolis, MN, U.S.A., pp. II-692-II-695, April 1993.
3. Bocchieri, E. & Mak, B. (1997). Subspace distribution clustering for continuous observation density HMMs. Proceedings of Eurospeech'97, Rhodes, Greece, September 1997.
4. Byrne, W. & Gunawardana, A. (1999). Convergence of EM variants. Proceedings of the 1999 Information Theory Workshop on Detection, Estimation, Classification and Imaging, Santa Fe, New Mexico, February 1999.
5. Digalakis, V., Monaco, P. & Murveit, H. (1996). Genones: Optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer. IEEE Transactions on Speech and Audio Processing, 4, 281-289.
6. Digalakis, V., Neumeyer, L. & Perakakis, M. (1998). Product-code vector quantization of cepstral parameters. Proceedings of the International Conference on Spoken Language Processing '98, Sydney, Australia.
7. Digalakis, V., Neumeyer, L. & Perakakis, M. (1999). Quantization of cepstral parameters for speech recognition over the WWW. IEEE Journal on Selected Areas in Communications, 17, 82-90.
8. Doddington, G. (1992). CSR corpus development. Proceedings of the ARPA Workshop on Spoken Language Technology, February 1992.
9. Jelinek, F. & Mercer, R. L. (1980). Interpolated estimation of Markov source parameters from sparse data. Proceedings of the Workshop on Pattern Recognition in Practice, Amsterdam, May 21-23.
10. Pallet, D., Fiscus, J. G., Fisher, W. M. & Garofolo, J. S. (1994). 1993 Benchmark tests for the ARPA spoken language program. Proceedings of the ARPA Workshop on Human Language Technology, Princeton, NJ, March 1994.
11. Price, P. (1990). Evaluation of spoken language systems: The ATIS domain. Proceedings of the Third DARPA Workshop, Hidden Valley, PA, U.S.A., June 1990.
12. Sabin, M. & Gray, R. M. (1984). Product code vector quantizers for waveform and voice coding. IEEE Transactions on Acoustics, Speech and Signal Processing, 32, 474-488.
13. Takahashi, S., Aikawa, K. & Sagayama, S. (1997). Discrete mixture HMM. Proceedings of the International Conference on Acoustics, Speech and Signal Processing '97, Munich, Germany.