Hidden-articulator Markov models for speech recognition

Speech Communication

Volumn 41, Issue 2-3, 2003, Pages 511-529

  Richardson, Matthew ^a   Bilmes, Jeff ^a   Diorio, Chris ^a  

^a University of Washington   (United States)

Author keywords

Articulatory models; Factorial HMM; Noise robustness; Speech recognition

Indexed keywords

ACOUSTIC NOISE; MARKOV PROCESSES; ROBUSTNESS (CONTROL SYSTEMS); SPEECH RECOGNITION;

NOISE ROBUSTNESS;

SPEECH COMMUNICATION;

EID: 0037697284     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(03)00031-1     Document Type: Article

References (34)

1. Bailly, G., et al., 1992. Inversion and speech recognition. Signal Processing VI: Proc. EUSIPCO-92, vol. 1, pp. 159-164.
2. Bilmes, J.A., 1999. Buried Markov models for speech recognition. ICASSP 1999, vol. 2, pp. 713-716.
3. Bilmes, J.A., 2000. Dynamic Bayesian multinets. Proc. 16th Conf. Uncertainty Artificial Intelligence, pp. 38-45.
4. Bishop C. Neural Networks for Pattern Recognition. 1995;Oxford University Press.
5. Blackburn, C., Young S., 1995. Towards improved speech recognition using a speech production model. Proc. Eurospeech, vol. 2, pp. 1623-1626.
6. Blomberg, M., 1991. Modelling articulatory inter-timing variation in a speech recognition system based on synthetic references. Proc. Eurospeech.
7. Deng L. Autosegmental representation of phonological units of speech and its phonetic interface. Speech Commun. 23(3):1997;211-222.
8. Deng L. A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition. Speech Commun. 24(4):1998;299-323.
9. Deng L., Sun D. A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features. J. Acoust. Soc. Amer. 95(5):1994;2702-2719.
10. Deng, L., Sun, D., 1994b. Phonetic classification and recognition using HMM representation of overlapping articulatory features for all classes of English sounds. ICASSP, pp. 45-48.
11. Deng L., Ramsay G., Sun D. Production models as a structural basis for automatic speech recognition. Speech Commun. 22(2):1997;93-111.
12. Dupont, S., et al. 1997. Hybrid HMM/ANN systems for training independent tasks: experiments on PHONEBOOK and related improvements. ICASSP, pp. 1767-1770.
13. Edwards H.T. Applied Phonetics: The Sounds of American English. second ed. 1997;Singular, San Diego.
14. Eide, E., Rohlicek, J.R., Gish, H., Mitter, S., 1993. A linguistic feature representation of the speech waveform. Proc. ICASSP, pp. 483-486.
15. Elenius, K., Blomberg, M., 1992. Comparing phoneme and feature based speech recognition using artificial neural networks. Proc. ICSLP, pp. 1279-1282.
16. Erler K., Freeman G.H. An HMM-based speech recognizer using overlapping articulatory features. J. Acoust. Soc. Amer. 100:1996;2500-2513.
17. Frankel, J., King, S., 2001. ASR - articulatory speech recognition. Proc. Eurospeech.
18. Frankel, J., Richmond, K., King, K., Taylor, P., 2000. An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory traces. Proc. ICSLP.
19. Ghahramani Z. Learning dynamic Bayesian networks. Lecture Notes in Artificial Intelligence. 1998;Springer-Verlag.
20. Hardcastle W.J., Hewlett N. Coarticulation. Theory, Data and Techniques. 1999;Cambridge.
21. Kirchhoff, K., 1998. Combining articulatory and acoustic information for speech recognition in noisy and reverberant environments. Proc. ICSLP, pp. 891-894.
22. Lauritzen S.L. Graphical Models. 1996;Oxford Science Publications.
23. Livescu, K., 2001, Segment-based recognition on the phone-book task: initial results and observations on durational modeling. Proc. Eurospeech.
24. Logan, B., Moreno, P., 1998. Factorial HMMs for acoustic modeling. ICASSP, pp. 813-816.
25. Picone, J., Pike, S., Regan, R., Kamm, T., Bridle, J., Deng, L., Ma, Z., Richards, H., Schuster, M., 1999. Initial evaluation of hidden dynamic models on conversational speech. Proc. ICASSP, pp. 109-112.
26. Pitrelli, J., Fong, C., Wong, S.H., Spitz, J.R., Lueng, H.C., 1995. PhoneBook: A phonetically-rich isolated-word telephone speech database. ICASSP, pp. 101-104.
27. Richardson, M., Bilmes, J., Diorio, C., 2000a. Hidden-Articulator Markov models for speech recognition. ASR 2000, pp. 133-139.
28. Richardson, M., Bilmes, J., Diorio, C., 2000b. Hidden-Articulator Markov models: performance improvements and robustness to noise. ICSLP 2000, vol. 3, pp. 131-134.
29. Rose R., Schroeter J., Sondhi M. The potential role of speech production models in automatic speech recognition. J. Acoust. Soc. Amer. 99:1996;1699-1709.
30. Saul L., Jordan M. Mixed memory Markov models: decomposing complex stochastic processes as mixtures of simpler ones. Machine-Learning. 37(1):1999;75-87.
31. Schmidbauer, O., 1989. Robust statistic modelling of systematic variabilities in continuous speech incorporating acoustic-articulatory relations. Proc. ICASSP, pp. 616-619.
32. Wrench, A., 2000. A Multichannel/Multispeaker Articulatory Database for Continuous Speech Recognition Research. Workshop on Phonetics and Phonology in ASR. Saarbruecken, Germany.
33. Young S. A review of large-vocabulary continuous-speech recognition. IEEE Signal Process. Mag. 13(5):1996;45-57.
34. Zweig, G., Russell, S., 1998. Speech recognition with dynamic bayesian networks. AAAI-98, pp. 173-180.