Speech recognition with unknown partial feature corruption - A review of the union model

Computer Speech and Language

Volumn 17, Issue 2-3, 2003, Pages 287-305

  Ming, Ji ^a   Smith, F Jack ^a  

^a QUEEN'S UNIVERSITY BELFAST   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; ALGORITHMS; MATHEMATICAL MODELS; STATISTICAL METHODS;

PARTIAL FEATURE CORRUPTION; UNION MODEL;

SPEECH RECOGNITION;

EID: 0038021371     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0885-2308(03)00003-2     Document Type: Article

References (35)

1. Baker, J., Cooke, M., Green, P., 2001, Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise. In: Proceedings of European Conference on Speech Communication and Technology '2001, Scandinavia, pp. 213-216.
2. Bourlard, H., Dupont, S., (1996). A new ASR approach based on independent processing and recombination of partial frequency bands. In: Proceedings of International Conference on Spoken Language Processing '96, Philadelphia, pp. 426-429.
3. Cerisara, C., Haton, J.-P., Mari, J.-F., Fohr, D., 1998. A recombination model for multi-band speech recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing '98, Seattle, pp. 717-720.
4. Christensen, H., Lindberg, B., Andersen, O., 2000. Employing heterogeneous information in a multi-stream framework. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing 2000, Istanbul, pp. 1571-1574.
5. Cooke, M., Morris, A., Green, P., 1997. Missing data techniques for robust speech recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing '97, Munich, pp. 803-806.
6. Cooke, M., Green, P., Josifovski, L., Vizinho, A., 2001. Robust automatic speech recognition with missing and unreliable acoustic data. Speech Communication 34, 267-285.
7. de Veth, J., Cranen, B., de Wet, F., Boves, L., 1999. Acoustic pre-processing for optimal effectivity of missing feature theory. In: Proceedings of European Conference on Speech Communication and Technology '99, Budapest, pp. 65-68.
8. Daoudi, K., Fohr, D., Antoine, C., 2000. A new approach for multi-band speech recognition based on probabilistic graphical models. In: Proceedings of International Conference on Spoken Language Processing 2000, Beijing.
9. Drygajlo, A., El-Maliki, M., 1998. Speaker verification in noisy environment with combined spectral subtraction and missing data theory. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing '98, Seattle, pp. 121-124.
10. Dupont, S., 1998. Missing data reconstruction for robust automatic speech recognition in the framework of hybrid HMM/ANN systems. In: Proceedings of International Conference on Spoken Language Processing '98, Sydney, pp. 1439-1442.
11. Dupont, S., Bourland, H., 1997. Using multiple time scales in a multi-stream speech recognition system. In: Proceedings of European Conference on Speech Communication and Technology '97, Rhodes, pp. 3-6.
12. Hariharan, R., Kiss, I., Viikki, O., Tian, J., 2000. Multi-resolution front-end for noise robust speech recognition. In: Proceedings of International Conference on Spoken Language Processing 2000, Beijing.
13. Hermansky, H., Tibrewala, S., Pavel, M., 1996. Towards ASR on partially corrupted speech. In: Proceedings of International Conference on Spoken Language Processing '96, Philadelphia, pp. 462-465.
14. Jancovic, P., Ming, J., 2001a. A probabilistic union model with automatic order selection for noisy speech recognition. Journal of Acoustic Society of America 110, 1641-1648.
15. Jancovic, P., Ming, J., 2001b. A multi-band approach based on the probabilistic union model and frequency-filtering features for robust speech recognition. In: Proceedings of European Conference on Speech Communication and Technology '01, Aalborg, pp. 1111-1114.
16. Josifovski, L., Cooke, M., Green, P., Vizinho, A., 1999. State based imputation of missing data for robust speech recognition and speech enhancement. In: Proceedings of European Conference on Speech Communication and Technology '99, Budapest, pp. 2837-2840.
17. Leonard, R.G., 1984. A database for speaker-independent digit recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing '84, San Diego, pp. 42.11/1-4.
18. 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: Proceedings of European Conference on Speech Communication and Technology '97, Rhodes, pp. 37-40.
19. McCourt, P., Vaseghi, S., Narte, N., 1998. Multi-resolution cepstral features for phone recognition across speech sub-bands. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing '98, Seattle, pp. 557-560.
20. Mirghafori, N., Morgan, N., 1998. Combining connectionist multi-band and full-band probability streams for speech recognition of natural numbers. In: Proceedings of International Conference on Spoken Language Processing '98, Sydney, pp. 743-747.
21. Morris, A., Hagen, A., Bourland, H., 1999, The full-combination sub-bands approach to noise robust HMM/ANN based ASR. In: Proceedings of European Conference on Speech Communication and Technology '99, Budapest, pp. 599-602.
22. Ming, J., 2001. An improved union model for continuous speech recognition with partial duration corruption. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding, Madonna di Campiglio, Trento.
23. Ming, J., Jancovic, P., Hanna, P., Stewart, D., Smith, F.J., 2000. Robust feature selection using probabilistic models. In: Proceedings of International Conference on Spoken Language Processing 2000, Beijing, pp. 546-549.
24. Ming, J., Jancovic, P., Hanna, P., Stewart, D., 2001. Modeling the mixtures of known noise and unknown unexpected noise for robust speech recognition. In: Proceedings of European Conference on Speech Communication and Technology '01, Aalborg, pp. 579-582.
25. 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, Tampere, pp. 175-178.
26. Ming, J., Smith, F.J., 2000. A probabilistic union model for sub-band based robust speech recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing 2000, Istanbul, pp. 1787-1790.
27. Ming, J., Smith, F.J., 2001. Union: a new approach for combining sub-band observations for noisy speech recognition. Speech Communication 34, 41-55.
28. Ming, J., Stewart, D., Hanna, P., Smith, F.J., 1999. A probabilistic union model for partial and temporal corruption of speech. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding, Keystone, CO, pp. 43-46.
29. Nadeu, C., Hernando, J., Gorricho, M., 1995. On the decorrelation of the filter-band energies in speech recognition. In: Proceedings of European Conference on Speech Communication and Technology '95, Madrid, pp. 1381-1384.
30. Okawa, S., Eorico, B., Potamianos, A., 1998. Multi-band speech recognition in noisy environments. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing '98, Seattle, pp. 641-644.
31. Raj, B., Singh, R., Stern, R.M., 1998. Inference of missing spectrographic features for robust speech recognition. In: Proceedings of International Conference on Spoken Language Processing '98, Sydney, pp. 1491-1494.
32. Renevey, P., Drygajlo, A., 2000. Statistical estimation of unreliable features for robust speech recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing 2000, Istanbul, pp. 1731-1734.
33. Seltzer, M.L., Raj, B., Stern, R.M., 2000. Classifier-based mask estimate for missing feature method of robust speech recognition. In: Proceedings of International Conference on Spoken Language Processing 2000, Beijing, China.
34. Vizinho, A., Green, P., Cooke, M., Josifovski, L., 1999. Missing data theory, spectral subtraction and signal-to-noise estimation for robust ASR: an integrated study. In: Proceedings of European Conference on Speech Communication and Technology '99, Budapest, Hungary, pp. 2407, 2410.
35. Wu, S., Kingsbury, B., Morgan, N., 1998. Performance improvements through combining phone- and syllable-length information in automatic speech recognition. In: Proceedings of International Conference on Spoken Language Processing '98, Sydney, pp. 854-857.