Speaker-adaptive learning of resonance targets in a hidden trajectory model of speech coarticulation

Computer Speech and Language

Volumn 21, Issue 1, 2007, Pages 72-87

  Yu, Dong ^a   Deng, Li ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN TRAJECTORY MODEL; SPEAKER ADAPTIVE LEARNING; SPEAKER INDEPENDENT; VOCAL TRACT RESONANCE (VTR);

ACOUSTIC PROPERTIES; ADAPTIVE SYSTEMS; LEARNING ALGORITHMS; LEARNING SYSTEMS; RESONANCE; SPEECH RECOGNITION;

SPEECH ANALYSIS;

EID: 33749541517     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2005.12.002     Document Type: Article

References (31)

1. Bakis, R., 1991. Coarticulation modeling with continuous-state HMMs. In: Proceedings of the IEEE Workshop Automatic Speech Recognition, Harriman, New York, pp. 20-21.
2. Bilmes J. Graphical models and automatic speech recognition. In: Johnson M., Ostendorf M., Khudanpur S., and Rosenfeld R. (Eds). Mathematical Foundations of Speech and Language Processing (2004), Springer, New York 135-186
3. Bridle, J., Deng, L., Picone, J., et al., 1998. An investigation of segmental hidden dynamic models of speech coarticulation for automatic speech recognition. Final Report for the 1998 Workshop on Language Engineering, Center for Language and Speech Processing at Johns Hopkins University, pp. 1-61.
4. Chelba C., and Jelinek F. Structured language modeling. Computer Speech Lang. October (2000) 283-332
5. 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
6. Deng L. Switching dynamic system models for speech articulation and acoustics. In: Johnson M., Ostendorf M., Khudanpur S., and Rosenfeld R. (Eds). Mathematical Foundations of Speech and Language Processing (2004), Springer, New York 115-134
7. Deng L., and Braam D. Context-dependent Markov model structured by locus equations: applications to phonetic classification. J. Acoust. Soc. Am. 96 (1994) 2008-2025
8. Deng L., and O'Shaughnessy D. Speech Processing - A Dynamic and Optimization-Oriented Approach (2003), Marcel Dekker, New York, NY
9. Deng, L., Lee, L., Attias, H., Acero, A., 2004a. A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances. In: IEEE Proceedings of ICASSP, May 2004, vol. I, pp. 557-560.
10. Deng, L., Yu, D., Acero, A., 2004b. A quantitative model for formant dynamics and contextually assimilated reduction in fluent speech. ICSLP 2004, Jeju, Korea.
11. Deng, L., Acero, A., Bazzi, I., 2006a. Tracking vocal tract resonances using a quantized nonlinear function embedded in a temporal constraint. IEEE Trans. Speech Audio Process 14 (2), in press.
12. Deng L., Yu D., and Acero A. A bi-directional target-filtering model of speech coarticulation and reduction: two-stage implementation for phonetic recognition. IEEE Trans. Speech Audio Process 14 1 (2006) 256-265
13. Eide, E., Gish, H., 1996. A parametric approach to vocal tract length normalization. In: IEEE Proceedings of ICASSP, pp. 346-348.
14. Gao, Y., Bakis, R., Huang, J., Zhang, B., 2000. Multistage coarticulation model combining articulatory, formant and cepstral features. In: Proceedings of ICSLP, vol. 1, pp. 25-28.
15. Holmes W., and Russell M. Probabilistic-trajectory segmental HMMs. Computer Speech Lang. 13 (1999) 3-37
16. Kamm T., Andreou G., and Cohen J. Vocal tract normalization in speech recognition: compensating for systematic speaker variability. Proceedings of the 15th Annual Speech Research Symposium (1995), CLSP, Johns Hopkins University, Baltimore, MD 161-167
17. Klatt D. Software for a cascade/parallel formant synthesizer. J. Acoust. Soc. Am. 99 3 (1980) 971-995
18. Lee L., and Rose R. A frequency warping approach to speaker normalization. IEEE Trans. Speech Audio Process. 6 (1998) 49-60
19. Ma J., and Deng L. Efficient decoding strategies for conversational speech recognition using a constrained nonlinear state-space model for vocal-tract-resonance dynamics. IEEE Trans. Speech Audio Process. 11 (2003) 590-602
20. McDonough, J., Byrne, W., Luo, X., 1998. Speaker normalization with all-pass transforms. In: Proceedings of ICSLP, vol. 6, pp. 2307-2310.
21. Naito M., Deng L., and Sagisaka Y. Speaker clustering for speech recognition using vocal-tract parameters. Speech Commun. 36 3-4 (2002) 305-315
22. Ostendorf M., Digalakis V., and Rohlicek J. From HMMs to segment models: a unified view of stochastic modeling for speech recognition. IEEE Trans. Speech Audio Process. 4 (1996) 360-378
23. Pye, D., Woodland, P.C., 1997. Experiments in speaker normalisation and adaptation for large vocabulary speech recognition. In: IEEE Proceedings of ICASSP, pp. 1047-1050.
24. Rose R., Schroeter J., and Sondhi M. The potential role of speech production models in automatic speech recognition. J. Acoust. Soc. Am. 99 (1996) 1699-1709
25. Sun J., and Deng L. An overlapping-feature based phonological model incorporating linguistic constraints: applications to speech recognition. J. Acoust. Soc. Am. 111 2 (2002) 1086-1101
26. Wang, W., Stolcke, A., Harper, M., 2004. The use of a linguistically motivated language model in conversational speech recognition. In: IEEE Proceedings of ICASSP, May 2004.
27. Wegmann, S., McAllaster, D., Orloff, J., Peskin, B., 1996. Speaker normalization on conversational telephone speech. In: IEEE Proceedings of ICASSP, pp. 339-341.
28. Welling, L., Haeb-Umbach, R., Aubert, X., Haberland, N., 1998. A study on speaker normalization using vocal tract normalization and speaker adaptive training. In: IEEE Proceedings of ICASSP, Seattle, WA, May 1998, vol. 2, pp. 797-800.
29. Zhan, P., Waibel, A., 1997. Vocal tract length normalization for large vocabulary continuous speech recognition. CMU-CS-97-148, Carnegie Mellon University, Pittsburgh, PA, May 1997.
30. Zhan, P., Westphal, M., 1997. Speaker normalization based on frequency warping. In: IEEE Proceedings of ICASSP, pp. 1039-1042.
31. Zhou, J., Seide, F., Deng. L., 2003. Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM. In: IEEE Proceedings of ICASSP, April 2003, vol. I, pp. 744-747.