Robust speech recognition in additive and convolutional noise using parallel model combination

Computer Speech and Language

Volumn 9, Issue 4, 1995, Pages 289-307

  Gales, M J F ^a   Young, S J ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0029390135     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1995.0014     Document Type: Article

References (18)

1. Abramowitz, M. & Stegen, I. A., editors (1965). Handbook of Mathematical Functions with Formulas, Graphs and Mathematical Tables. Dover Publications, New York.
2. Beattie, V. L. & Young, S. J. (1992). Hidden Markov model state-based Cepstral noise compensation. Proceedings of the ICSLP 1, 519-522.
3. Berstein, A. D. & Shallom, I. D. (1991). An hypothesized Wiener filtering approach to noisy speech recognition. Proceedings of the ICASSP 2, 913-916.
4. Davis, S. B. & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions ASSP 28, 357-366.
5. Furui, S. (1992). Toward robust speech recognition under adverse conditions. Proceedings of the ESCA Workshop in Speech Processing in Adverse Conditions, pp. 31-42.
6. Gales, M. J. F. & Young, S. J. (1993a). Cepstral parameter compensation for HMM recognition in noise. Speech Communication 121, 231-240.
7. Gales, M. J. F. & Young, S. J. (1993b). PMC for speech recognition in additive and convolutional noise. Technical Report CUED/F-INFENG/TR154. Available via anonymous ftp from: svr-ftp.eng.cam.ac.uk.
8. Gales, M. J. F. & Young, S. J. (1995). A fast and flexible implementation of parallel model combination. Proceedings of the ICASSP 1, 133-136.
9. Juang, B. H. & Rabiner, L. R. (1985). A probabilistic distance measure for hidden Markov models. AT&T Technical Journal 64, 391-408.
10. Kadirkamanathan, M. & Varga, A. P. (1991). Simultaneous model re-estimation from contaminated data by "Composed hidden Markov modelling". Proceedings of the ICASSP 2, 897-900.
11. Minami, Y. & Furui, S. (1985). A maximum likelihood procedure for a universal adaptation method based on HMM composition. Proceedings of the ICASSP 1, 129-132.
12. Moreno, P. J., Raj, B., Gouvea, E. & Stern, R. M. (1995). Multivariate-Gaussian-based Cepstral normalization for robust speech recognition. Proceedings of the ICASSP 1, 137-140.
13. Openshaw, J. P. & Mason, J. S. (1994). On the limitations of Cepstral features in noise. Proceedings of the ICASSP 2, pp. II49-II52.
14. Sankar, A. & Lee, C. H. (1995). Robust speech recognition based on stochastic matching. Proceedings of the ICASSP 1, 121-124.
15. Varga, A. P., Moore, R., Bridle, J., Ponting, K. & Russell, M. (1988). Noise compensation algorithms for use with hidden Markov model based speech recognition. Proceedings of the ICASSP 1, pp. 481-484.
16. Varga, A. P. & Moore, R. K. (1990). Hidden Markov model decomposition of speech and noise. Proceedings of the ICASSP 2, 845-848.
17. Varga, A. P., 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.
18. Young, S. J. (1992). HTK Version 1.4: Reference Manual and User Manual. Cambridge University Engineering Department Speech Group.