Improvement of noisy speech recognition using a proportional alignment decoding algorithm in the training phase

Computer Speech and Language

Volumn 12, Issue 3, 1998, Pages 165-192

  Hung, Wei Wen ^a   Wang, Hsiao Chuan ^b  

^a MING CHI UNIVERSITY OF TECHNOLOGY   (Taiwan)

^b NATIONAL TSING HUA UNIVERSITY   (Taiwan)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; ALGORITHMS; DECODING; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY DENSITY FUNCTION;

HIDDEN MARKOV MODELS (HMM); PROPORTIONAL ALIGNMENT DECODING (PAD) ALGORITHMS;

SPEECH RECOGNITION;

EID: 0041353733     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1998.0046     Document Type: Article

References (21)

1. Anastasakos, A., Schwartz, R. & Shu, H. (1995). Duration modeling in large vocabulary speech recognition. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Detroit, Michigan, pp. 628-631.
2. Bonafonte, A., Vidal, J. & Nogueiras, A. (1996). Duration modeling with Expanded HMM applied to Speech Recognition. Proceedings of International Conference on Spoken Language Processing, Philadelphia, PN, pp. 1097-1100.
3. Burshtein, D. (1995). Robust parametric modeling of durations in hidden Markov models. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Detroit, MI, pp. 548-551.
4. Gu, H. Y., Tseng, C. Y. & Lee, L. S. (1991). Isolated-Utterance speech recognition using hidden Markov models with bounded state durations. IEEE Transactions on Signal Processing, 39, 1743-1752.
5. Hung, W. W. & Wang, H. C. (1997). HMM retraining based on state duration alignment for noisy speech recognition. Proceedings of European Conference on Speech Communication and Technology (EUROSPEECH), 3, 1519-1522.
6. Juang, B. H. & Rabiner, L. R. (1985). Mixture autoregressive hidden Markov models for speech signals. IEEE Transactions on Acoustics Speech and Signal Processing, 33, 1404-1413.
7. Juang, B. H. & Rabiner L. R. (1990). The segmental k-means algorithm for estimating parameters of hidden Markov models. IEEE Transactions On Acoustics, Speech, Signal Processing, 38, 1639-1641.
8. Kim, W. G., Yoon, J. Y. & Youn, D. H. (1994). HMM with global path constraint in Viterbi decoding for isolated word recognition. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Adelaide, Australia, pp. 605-608.
9. Laurila, K. (1997). Noise robust speech recognition with state duration constraints. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Munich, Germany, pp. 871-874.
10. Lee, L. M. & Wang, H. C. (1994). A study on adaptation of cepstral and delta cepstral coefficients for noisy speech recognition. Proceedings of International Conference on Spoken Language Processing, Yokohama, Japan, pp. 1011-1014.
11. Levinson, S. E. (1986). Continuously variable duration hidden Markov models for speech analysis. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Tokyo, Japan, pp. 1241-1244.
12. Power, K. (1996). Durational modeling for improved connected digit recognition. Proceedings of International Conference on Spoken Language Processing, Philadelphia, PN, pp. 885-888.
13. Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77, 257-286.
14. Rabiner, L. R., Juang, B. H., Levinson, S. E. & Sondhi, M. M. (1985). Recognition of isolated digits using hidden Markov models with continuous mixture densities. AT&T Technical Journal, 64, 1211-1234.
15. Rabiner, L. R., Wilpson, J. G. & Juang, B. H. (1986). A segmental k-means training procedure for connected word recognition. AT&T Technical Journal, 65, 21-31.
16. Rabiner, L. R., Wilpson, J. G. & Soong, F. K. (1988). High performance connected digit recognition, using hidden Markov models. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, New York, NY, pp. 119-122.
17. Russell, M. J. & Cook, A. E. (1987). Experimental evaluation of duration modeling techniques for automatic speech recognition. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Dallas, TX, pp. 2376-2379.
18. Russell, M. J. & Moore, R. K. (1985). Explicit modeling of state occupancy in hidden Markov models for automatic speech recognition. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Tampa, FL, pp. 5-8.
19. Varga, A. Steeneken, H. J. M., Tomlinson, M. & Jones, D. (1992). The NOISEX-92 study on the effect of additive noise on automatic speech recognition, Technical Report, DRA Speech Research Unit, Malvern, England.
20. Vaseghi, S. V. (1995). State duration modeling in hidden Markov models. Signal Processing, 41, 31-41.
21. Zeljkovic, I. (1996). Decoding optimal state sequence with smooth state likelihoods. Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing, Atlanta, GA, pp. 129-132.