Multi-stream adaptive evidence combination for noise robust ASR

Speech Communication

Volumn 34, Issue 1-2, 2001, Pages 25-40

  Morris, Andrew ^a   Hagen, Astrid ^a   Glotin, Hervé ^a   Bourlard, Hervé ^a,b  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b EPFL   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC VARIABLES CONTROL; ADAPTIVE FILTERING; DATA STRUCTURES; MARKOV PROCESSES; MATHEMATICAL MODELS; NEURAL NETWORKS; PROBABILITY DISTRIBUTIONS; ROBUSTNESS (CONTROL SYSTEMS); SPEECH ANALYSIS; SPEECH SYNTHESIS;

HIDDEN MARKOV MODELS; MULTI-STREAM ADAPTIVE EVIDENCE COMBINATION METHOD;

CONTINUOUS SPEECH RECOGNITION;

EID: 0034825241     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(00)00044-3     Document Type: Article

References (47)

1. Allen, J.B., 1994. How do humans process and recognise speech?. IEEE Trans. Speech Signal Process. 2 (4), 567-576.
2. Berthommier, F., Glotin, H., 1999. A new SNR-feature mapping for robust multi-stream speech recognition. In: Proc. ICPhS'99, pp. 711-715.
3. Bishop, C. (Ed.), 1995. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, pp. 365-368.
4. Bourlard, 1999. Non-stationary multi-channel (multi-stream, processing towards robust and adaptive ASR. In: Proceedings of Tampere Workshop on Robust Methods for Speech Recognition in Adverse Conditions, pp. 1-10.
5. Bourlard, H., Dupont, S., 1996. A new ASR approach based on independent processing and recombination of partial frequency bands. In: Proc. ICSLP'96, Philadelphia, pp. 422-425.
6. Bourlard, H., Morgan, N., 1994. Connectionist speech recognition - a hybrid approach. Kluwer Academic Publishers, Dordrecht.
7. Bourlard, H., Morgan, N., 1997. Hybrid HMM/ANN systems for speech recognition: overview and new research directions. In: Proceedings of International School on Neural Nets: Adaptive Processing of Temporal Information.
8. Cole, R.A., Noel, T., Lander, L., Durham, T., 1995. New telephone speech corpora at CSLU. In: Proceedings of European Conference on Speech Communication and Technology, Vol. 1, pp. 821-824.
9. de Veth, J., de Wet, F., Cranen, B., Boves, L., 1999. Missing feature theory in ASR: make sure you missing the right type of features. In: Proceedings of Workshop on Robust Methods for Speech Recognition in Adverse Conditions, pp. 231-234.
10. Duda, R.O., Hart, P.E., 1993. Pattern Classification and Scene Analysis. Wiley, New York.
11. Dupont, S., Luettin, J., 1998. Using the multi-stream approach for continuous audio-visual speech recognition: experiments on the M2VTS database. In: Proc. ICSLP'98, pp. 1283-1286.
12. Fletcher, H., 1922. The nature of speech and its interpretation. J. Franklin Inst. 193 (6), 729-747.
13. Gales, M.J.F., Young, S.J., 1993. HMM recognition in noise using parallel model combination. In: Proc. Eurospeecl'93, pp. 837-840.
14. Girin, L., Feng, G., Schwartz, J.-L., 1998. Fusion of auditory and visual information for noisy speech enhancement: a preliminary study of vowel transitions. In: Proc. ICASSP'98, pp. 1005-1008.
15. Glotin, H., Berthommier, F., Tessier, E., 1999. A CASA-labelling model using the localisation cue for robust cocktail-party speech recognition. In: Proc. Eurospeech'99, pp. 2351-2354.
16. Greenberg, S., 1997. On the origins of speech intelligibility in the real world. In: Proceedings ESCA Workshop on Robust Speech Recognition for Unknown Communication Channels, pp. 23-32.
17. Hagen, A., Morris, A.C., Bourlard, H., 1999. Different weighting schemes in the full combination sub-bands approach for noise robust ASR. In: Proceedings Tampere Workshop on Robust Methods for Speech Recognition in Adverse Conditions, pp. 199-202.
18. Hennebert, J., Ris, C., Bourlard, H., Renals, S., Morgan, N., 1997. Estimation of global posteriors and forward-backward training of hybrid systems. In: Proc. Eurospeech'97, pp. 1951-1954.
19. Hermansky, H., 1990. Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87 (4), 1738-1752.
20. Hermansky, H., Morgan, N., 1994. RASTA processing of speech. IEEE Trans. Speech Audio Process. 2 (4), 578-589.
21. Hermansky, H., Sharma, S., 1999. Temporal patterns (TRAPS) in ASR noisy speech. In: Proc. ICASSP'99, pp. 298-292.
22. Hermansky, H., Tibrewela, S., Pavel, M., 1996. Towards ASR on partially corrupted speech. In: Proc. ICSLP'96, pp. 462-465.
23. Hirsch, H.G., Ehrlicher, C., 1995. Noise estimation techniques for robust speech recognition. In: ICASSP95, pp. 153-156.
24. Jordan, M.I., Jacobs, R.A., 1994. Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6, 181-214.
25. Kingsbury, B., Morgan, N., Greenberg, S., 1998. Robust speech recognition using the modulation spectrogram. Speech Communication 25 (1-3), 117-132.
26. Lippmann, R.P., Carlson, B.A., 1997. Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise. In: Proc. Eurospeech'97, pp. 37-40.
27. McGurk, H., McDonald, J., 1976. Hearing lips and seeing voices. Nature 264, 746-748.
28. Ming, J., Smith, F.J., 1999. Union: a new approach for combining sub-band observations for noisy speech recognition. In: Proceedings of Workshop on Robust Methods for Speech Recognition in Adverse Conditions, pp. 175-178.
29. Mirghafori, N., 1999. A multi-band approach to automatic speech recognition. PhD Dissertation, University of California at Berkeley, December 1998. Reprinted as ICSI Technical Report, ICSI TR-99-04.
30. Moore, B.C.J., 1997. An Introduction to the Psychology of Hearing, 4th edition. Academic Press, New York.
31. Morgan, N., Bourlard, H., Hermansky, H., 1998. Automatic speech recognition: an auditory perspective. Research Report IDIAP-RR 98-17.
32. Morris, A.C., 1999. Latent variable decomposition for posteriors or likelihood based sub-band ASR. Research Report IDIAP-Com 99-04.
33. Morris, A.C., Cooke, M., Green, P., 1998. Some solutions to the missing feature problem in data classification, with application to noise robust ASR. In: Proc. ICASSP'98, pp. 737-740.
34. Morris, A.C., Hagen, A., Bourlard, H., 1999. The full-combination sub-bands approach to noise robust HMM/ANN based ASR. In: Proc. Eurospeech'99, pp. 599-602.
35. Nadeu, C., Hernando, J., Gorricho, M., 1995. On the decorrelation of filterbank energies in speech recognition. In: Proc. Eurospeech'95, pp. 1381-1384.
36. Okawa, S., Boccieri, E., Potamianos, A., 1998. Multi-band speech recognition in noisy environment. In: Proc. ICASSP'98, pp. 641-644.
37. Pickles, J.O., 1988. An Introduction to the Physiology of Hearing. Academic Press, New York.
38. Rao, S., Pearlman, W.A., 1996. Analysis of linear prediction, coding and spectral estimation from sub-bands. IEEE Trans. Inf. Theory 42, 1160-1178.
39. Raviv, Y., Intrator, N., 1996. Bootstraping with noise: an effective regularisation technique. Connection Sci., Special Issue on Combining Estimators, 8, 356-372.
40. Richard, M.D., Lippmann, R.P., 1991. Neural network classifiers estimate Bayesian a-posteriori probabilities. J. Neural Comput. 3 (4), 461-483.
41. Steeneken, H.J.M., Houtgast, T., 1999. Mutual dependence of the octave-band weights in predicting speech intelligibility. Speech Communication 28 (2), 109-123.
42. Tomlinson, J., Russel, M.J., Brooke, N.M., 1996. Integrating audio and visual information to provide highly robust speech recognition. In: Proc. ICASSP'96, pp. 821-824.
43. Tomlinson, J., Russel, M.J., Moore, R.K., Bucklan, A.P., Fawley, M.A., 1997. Modelling asynchrony in speech using elementary single-signal decomposition. In: Proc. ICASSP'97, pp. 1247-1250.
44. Varga, A., Moore, R., 1990. Hidden Markov model decomposition of speech and noise. In: Proc. ICASSP'90, pp. 845-848.
45. 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.
46. Westphal, M., Waibel, A., 1999. Towards spontaneous speech recognition for on-board car navigation and information systems. In: Proc. Eurospeech'99, pp. 1955-1958.
47. Wu, S.-L., Kingsbury, B.E., Morgan, N., Greenberg, S., 1998. Performance improvements through combining phone and syllable scale information in automatic speech recognition. In: Proc. ICASSP'98, pp. 459-462.