Low cost duration modelling for noise robust speech recognition

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 1025-1028

  Morris, Andrew C ^a   Payne, Simon ^a,b   Bourlard, Hervé ^a,c  

^a DALLE MOLLE INSTITUTE FOR ARTIFICIAL INTELLIGENCE IDSIA   (Switzerland)

^b UNIVERSITY OF SHEFFIELD   (United Kingdom)

^c EPFL   (Switzerland)

Author keywords

Duration models; HMMs; Noise robust ASR

Indexed keywords

DURATION MODELLING; DURATION MODELS; HMMS; NOCV2; NOISE ROBUST ASR; NOISE ROBUST SPEECH RECOGNITION; NOISY SPEECH RECOGNITION; STATE TRANSITION MATRIX; STATE TRANSITION PROBABILITIES;

SPEECH RECOGNITION;

EID: 85009253205     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. Bilmes, J., N. Morgan, N., Wu, S.-L. & Bourlard, H. (1996) "Stochastic Perceptual Speech Models With Durational Dependence", Proc. ICSLP'96, pp. 1301-1304.
2. Birshtein, D. (1995) "Robust parametric modelling of durations in hidden Markov models", Proc. ICASSP'95, pp. 548-551.
3. Bourlard, H. (1997) "State-of-the-Art and Recent Progress in Hybrid HMM/ANN Speech Recognition", Proc. ICANN'97.
4. Evans, M., Hastings, N. & Peacock, B. (2000) Statistical Distributions, Wiley series in probability and statistics.
5. Levinson, S. E. (1986) "Continuously variable duration hidden Markov models for automatic speech recognition", Computer Speech and Language, Vol. 1, pp. 29-45.
6. McCowan, L. A., Morris, A. C. & Bourlard, B. (2002) "Improving speech recognition performance of small microsphone arrays using missing data techniques", Proc ICSLP'02 (in press).
7. Morgan, N., Fosler, E., and Mirghafori, N. (1997) "Speech recognition using on-line estimation of speaking rate", Proc. Eurospeech'97, pp. 2079-2082.
8. Morris, A. C. (2002) "An information theoretic measure of sequence recognition performance", IDIAP TR com02-03.
9. Morris, A. C, Hagen, A. & Bourlard, H. (2001) "MAP Combination of Multi-Stream HMM or HMM/ANN Experts", Proc. Eurospeech 2001, pp. 225-228.
10. Pearce, D. & Hirsch, H.-G. (2000) "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions", Proc. ICSLP'00, Vol. 4, pp. 29-32.
11. Power, K. (1996) "Duration Modelling for improved connected digit recognition", Proc. ICSLP'96, pp. 885-888.
12. Russel, M. J. and Moore, R. K. (1985) "Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition", Proc. ICASSP'85, pp. 5-8.