Parameter reduction schemes for loosely coupled HMMs

Computer Speech and Language

Volumn 17, Issue 2-3, 2003, Pages 233-262

  Nock, H J ^a   Ostendorf, M ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; STATE SPACE METHODS; TOPOLOGY;

HIDDEN MARKOV MODELS; MULTIBAND MODELS; PARAMETER REDUCTION;

SPEECH RECOGNITION;

EID: 0038697760     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0885-2308(03)00009-3     Document Type: Article

References (56)

1. Baum, L.E., Petrie, T., Soules, G., Weiss, N., 1970. A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Annals of Mathematical Statistics 41 (1), 164-171.
2. Bourlard, H., Dupont, S., Ris, C., 1996. Multi-stream speech recognition. Technical Report IDIAP-RR 96-07, IDIAP.
3. Brand, M., Oliver, N., Pentland, A., 1997. Coupled hidden Markov models for complex action recognition. In: Proceedings of IEEE CVPR, pp. 994-999.
4. Byrne, W., Finke, M., Khudanpur, S., McDonough, J., Nock, H., Riley, M., Saraclar, M., Wooters, C., Zavaliagkos, G., 1998. Pronunciation modelling using a hand-labelled corpus for conversational speech recognition. In: Proceedings of ICASSP, pp. 313-316.
5. Cole, R., Muthusamy, Y., Fanty, M., 1990. The ISOLET spoken letter database. Technical Report CSE 90-004, OGI.
6. Daoudi, K., Fohr, D., Antoine, C., 2000. A new approach for multi-band speech recognition based on probabilistic graphical models. In: Proceedings of ICSLP, pp. I:329-332.
7. Dempster, A.P., Laird, N.M., Rubin, D.B., 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society 39 (1), 1-38.
8. Deng, L., Erler, K., 1992. Structural design of a hidden Markov model based speech recognizer using multi-valued phonetic features: comparison with segmental speech units. Journal of the Acoustical Society of America 92 (92), 3058-3067.
9. Finke, M., Fritsch, J., Koll, D., Waibel, A., 1999. Modeling and efficient decoding of large vocabulary conversational speech. In: Proceedings of Eurospeech, pp. 467-470.
10. Finke, M., Waibel, A., 1997. Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition. In: Proceedings of Eurospeech, pp. 2379-2382.
11. Gales, M.J.F., 1995. Model-based techniques for noise robust speech recognition. PhD Thesis, Cambridge University Engineering Dept., Cambridge, UK.
12. Ghahramani, Z., Jordan, M.I., 1997. Factorial hidden Markov models. Machine Learning 29, 245-273.
13. Gillick, L., Cox, S.J., 1989. Some statistical issues in the comparison of speech recognition algorithms. In: Proceedings of ICASSP, pp. 532-535.
14. Hain, T., Woodland, P.C., 1999. Dynamic HMM selection for continuous speech recognition. In: Proceedings of Eurospeech, pp. 532-535.
15. Hain, T., Woodland, P.C., 2000. Modelling sub-phone insertions and deletions in continuous speech recognition. In: Proceedings of ICSLP, pp. IV:172-175.
16. Hain, T., Woodland, P.C., Evermann, G., Povey, D., 2000. The CU-HTK march 2000 Hub5e transcription system. In: Proceedings of Speech Transcription Workshop.
17. Hermansky, H., Tibrewala, S., Pavel, M., 1996. Towards ASR on partially corrupted speech. In: Proceedings of ICSLP. pp. 462-465.
18. Huckvale, M.A., 1994. Word recognition from tiered phonological models. In: Proceedings of Institute of Acoustics Conference on Speech and Hearing, vol. 16, pp. 163-170.
19. Humphries, J.J., Woodland, P.C., 1997. Using accent-specific pronunciation modelling for improved large vocabulary continuous speech recognition. In: Proceedings of Eurospeech, pp. 2367-2370.
20. Kapadia, S., 1998. Discriminative training of hidden Markov models. PhD Thesis, Cambridge University Engineering Dept., Cambridge, UK.
21. Keating, P., 1997. Word-level phonetic variation in large speech corpora. In: Pompino-Marschal, B. (Ed.), ZAS Working Papers in Linguistics. Available from
22. King, S., Stephenson, T., Isard, S., Taylor, P., Strachan, A., 1998. Speech recognition via phonetically featured syllables. In: Proceedings of ICSLP, vol. 3, pp. 1031-1034.
23. King, S., Taylor, P., 2000. Detection of phonological features in continuous speech using neural networks. Computer Speech and Language 14 (4), 333-353.
24. Kingsbury, P., Strassel, S., McLemore, C., 1997. COMLEX pronouncing lexicon (renamed in 1997 release as CALLHOME American English lexicon). Available from Linguistic Data Consortium
25. Kirchhoff, K., 1999. Robust speech recognition using articulatory information. PhD Thesis, University of Bielefeld, Germany.
26. Lamel, L., Adda, G., 1996. On designing pronunciation lexicons for large vocabulary, continuous speech recognition. In: Proceedings of ICSLP, pp. 6-9.
27. Lauritzen, S.L., 1996. Graphical Models. Claredon, Oxford.
28. Leonard, R. G., 1984. A database for speaker-independent digit recognition. In: Proceedings of ICASSP, pp. 42.11-14.
29. Linde, Y., Buzo, A., Gray, R.M., 1980. An algorithm for vector quantizer design. IEEE Transactions Communications 28, 84-95.
30. Logan, B., Moreno, P.J., 1997. Factorial hidden Markov models for speech recognition: preliminary experiments. Technical Report 97/7, Cambridge Research Laboratory.
31. Mak, B., Tam, Y.-C., 2000. Asynchrony with trained transition probabilities improves performance in multi-band speech recognition. In: Proceedings of ICSLP, pp. IV:149-152.
32. McMahon, P., McCourt, P., Vaseghi, S., 1998. Discriminative weighting of multi-resolution sub-band cepstral features for speech recognition. In: Proceedings of ICSLP, pp. 1055-1058.
33. Mirghafori, N. 1999. A Multi-band approach to automatic speech recognition. PhD Thesis, ICSI, UC Berkeley, CA, USA.
34. Neti, C., Potamianos, G., Luettin, J., Matthews, I., Herve Gtin, Vergyri, D., Sison, J., Mashari, J., Zhou, J., 2000. Audio-visual speech recognition. Technical Report, The Johns Hopkins University (Center for Language and Speech Processing) Summer Research Workshop.
35. NIST. Score package. Available from.
36. Nock, H.J., 2001. Techniques for modelling phonological processes in automatic speech recognition. PhD Thesis, Cambridge University Engineering Dept., Cambridge, UK, August.
37. Nock, H.J., Young, S.J., 2000. Loosely-coupled HMMs for ASR. In: Proceedings of ICSLP, pp. III:143-146.
38. Nock, H.J., Young, S.J., 2002. Modelling asynchrony in automatic speech recognition using loosely coupled hidden Markov models. Cognitive Science 26 (3), 283-301.
39. Odell, J., 1995. The use of context in large vocabulary speech recognition. PhD Thesis, Cambridge University Engineering Dept., Cambridge, UK.
40. Ostendorf, M., 2000. Incorporating linguistic theories of pronunciation variation into speech recognition models. In: Philosophical Transactions of Royal Society, vol. 358, London, UK, pp. 1325-1338.
41. Ostendorf, M., Singer, H., 1997. HMM topology design using maximum likelihood successive state splitting. Computer Speech and Language 11, 17-41.
42. Rabiner, L., Juang, B.-H., 1993. Fundamentals of Speech Recognition. Prentice-Hall, New Jersey.
43. Rabiner, L.R., 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of IEEE 77(2), 257-285.
44. Richmond, K., 2001. Mixture density networks, human articulatory data and acoustic-to-articulatory inversion of continuous speech. In: Proceedings of Institute of Acoustics WISP 2001, Stratford-upon-Avon, UK.
45. Riley, M.D., 1991. A statistical model for generating pronunciation networks. In: Proceedings of ICASSP, pp. 737-740.
46. Saraclar, M., 2000. Pronunciation modeling for conversational speech recognition. PhD Thesis, The Johns Hopkins University, MD, USA.
47. Saraclar, M., Nock, H., Khudanpur, S., 2000. Pronunciation modeling by sharing Gaussian densities across phonetic models. Computer Speech and Language 14 (2), 137-160.
48. Saul, L. K., Jordan, M.I., 1999. Mixed memory Markov models. Machine Learning 37, 75-87.
49. Tomlinson, M.J., Russell, M.J., Brooke, N.M., 1996. Integrating audio and visual information to provide highly robust speech recognition. In: Proceedings of ICASSP, vol. II, pp. 821-824.
50. Tomlinson, M.J., Russell, M.J., Moore, R.K., Buckland, A.P., Fawley, M.A. 1997. Modelling asynchrony in speech using elementary single-signal decomposition. In: Proceedings of ICASSP, pp. 1247-1250.
51. Varga, A.P., Moore, R.K., 1990. Hidden Markov model decomposition of speech and noise. In: Proceedings of ICASSP, pp. 845-848.
52. Vaxeclaire, B., Sock, R., Perrier, P., 2000. Gestural overlap, place of articulation and speech rate: an X-ray investigation. In: Proceedings of ICSLP, pp. II:166-II:169.
53. Weintraub, M., Stolcke, A., Sankar, A., 1995. SRI Switchboard progress and experiments. In: Proceedings of DARPA LVCSR Workshop.
54. Weintraub, M., Wegmann, S., Kao, Y.-H., Khudanpur, S., Galles, C., Fosler, E., Saraclar, M., 1996. Automatic learning of word pronunciation from data. Technical Report, The Johns Hopkins University (Center for Language and Speech Procesing) Summer Research Workshop.
55. Wilkinson, N., Russell, M.J., 2001. Progress towards improved speech modelling using asynchronous sub-bands and formant frequencies. In: Proceedings of Institute of Acoustics WISP, Stratford-upon-Avon, UK.
56. Young, S., Jansen, J., Odell, J., Ollason, D., Woodland, P., 1995. The HTK Book (Version 2.0), ECRL.