A bidirectional target-filtering model of speech coarticulation and reduction: Two-stage implementation for phonetic recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 1, 2006, Pages 256-265

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

^a MICROSOFT RESEARCH   (United States)

Author keywords

Cepstral dynamics; Contextual assimilation; Filtering of targets; Formant dynamics; Long span context dependence; Phonetic recognition; Phonetic reduction; Resonances; TIMIT

Indexed keywords

ACOUSTIC WAVES; FIR FILTERS; IMPULSE RESPONSE; MARKOV PROCESSES; MATHEMATICAL MODELS; RESONANCE;

CEPSTRAL DYNAMICS; CONTEXTUAL ASSIMILATION; FILTERING OF TARGETS; LONG-SPAN CONTEXT DEPENDENCE; PHONETIC REDUCTION; TIMIT;

SPEECH RECOGNITION;

EID: 33744966561     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.854107     Document Type: Conference Paper

References (33)

1. R. Bakis, "Coarticulation modeling with continuous-state HMMs," in Proc. IEEE Workshop Automatic Speech Recognition, New York, 1991. pp. 20-21.
2. J. Bilmes, "Graphical models and automatic speech recognition," in Mathematical Foundations of Speech and Language Processing, M. Johnson, M. Ostendorf, S. Khudanpur, and R. Rosenfeld, Eds. New York: Springer-Verlag, 2004, pp. 135-186.
3. J. Bridle et al., "An investigation of segmentai hidden dynamic models of speech coarticulation for automatic speech recognition," in Proc. Final Report Workshop on Language Engineering, Center for Language and Speech Processing at The Johns Hopkins University, 1998, pp. 1-61.
4. C. Chelba and F. Jelinek, "Structured language modeling," Compur. Speech Lang., pp. 283-332, Oct. 2000.
5. L. Deng, "A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal," Signal Process., vol. 27, pp. 65-78, 1992.
6. _, "A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition," Speech Commun., vol. 24. no. 4, pp. 299-323, 1998.
7. _, "Computational models for speech production," in Computational Models of Speech Pattern Processing, K. Ponting, Ed. Berlin, Germany: Springer-Verlag, 1999, pp. 199-213.
8. _, "Switching dynamic system models for speech articulation and acoustics," in Mathematical Foundations of Speech and Language Processing, M. Johnson, M. Ostendorf, S. Khudanpur, and R. Rosenfeld, Eds. New York: Springer-Verlag, 2004, pp. 115-134.
9. L. Deng and D. O'Shaughnessy, SPEECH PROCESSING - A Dynamic and Optimization-Oriented Approach. New York: Marcel Dekker, 2003.
10. L. Deng and D. Braam, "Context-dependent Markov model structured by locus equations: Applications to phonetic classification," J. Acoust. Soc. Amer., vol. 96, pp. 2008-2025, Oct. 1994.
11. L. Deng, L. Lee, H. Attias, and A. Acero, "A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances," in Proc. IEEE ICASSP, vol. I, May 2004. pp. 557-560.
12. L. Deng, A. Acero, and I. Bazzi, "Tracking vocal tract resonances using a quantized nonlinear function embedded in a temporal constraint," IEEE Trans. Speech Audio Process., to be published.
13. J. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Proc. Automatic Speech Recognition and Understanding, 1997, pp. 347-354.
14. Y. Gao, R. Bakis, J. Huang, and B. Zhang, "Multistage coarticulation model combining articulatory, formant and cepstral features," in Proc. ICSLP, vol. 1, 2000, pp. 25-28.
15. T. Gay, "Effect of speaking rate on vowel formant movements," J. Acoust. Soc. Amer., vol. 63, pp. 223-230, 1978.
16. M. Siu, R. Iyer, H. Gish, and C. Quillen, "Parametric trajectory mixtures for LVCSR," in Proc. ICSLP, Sydney, Australia, 1998, pp. 3269-3272.
17. S. Hertz, "Streams, phones, and transitions: Toward a new phonological and phonetic model of formant timing," J. Phonet., vol. 19, pp. 91-109, 1991.
18. B. Lindblom, "Spectrographic study of vowel reduction," J. Acoust. Soc. Amer., vol. 35, pp. 1773-1781, 1963.
19. W. Holmes and M. Russell, "Probabilistic-trajectory segmental HMMs," Comput. Speech Lang., vol. 13, pp. 3-37, 1999.
20. D. Klatt, "Software for a cascade/parallel formant synthesizer," J. Acoust. Soc. Amer., vol. 99, no. 3, pp. 971-995, 1980.
21. B. Lindblom, "Explaining phonetic variation: A sketch of the H & H theory," in Speech Production and Speech Modeling, W. Hardcastle and A. Marchal, Eds. Norwell, MA: Kluwer, 1990, pp. 403-439.
22. J. Ma and L. Deng, "Efficient decoding strategies for conversational speech recognition using a constrained nonlinear state-space model for vocal-tract-resonance dynamics," IEEE Trans. Speech Audio Process., vol. 11, no. 6, pp. 590-602, Nov. 2003.
23. S. Moon and B. Lindblom, "Interaction between duration, context, and speaking style in English stressed vowels," J. Acoust. Soc. Amer., vol. 96, pp. 40-55, 1994.
24. M. Ostendorf, V. Digalakis, and J. Rohlicek, "From HMM's to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans. Speech Audio Process., vol. 4, no. 5, pp. 360-378, Sep. 1996.
25. M. Pitermann, "Effect of speaking rate and contrastive stress on formant dynamics and vowel perception," J. Acoust. Soc. Amer., vol. 107, pp. 3425-3437, 2000.
26. L. Pols, "Psycho-acoustics and speech perception," in Computational Models of Speech Pattern Processing, K. Ponting, Ed. Berlin, Germany: Springer-Verlag, pp. 10-17.
27. R. Rose, J. Schroeter, and M. Sondhi, "The potential role of speech production models in automatic speech recognition," J. Acoust. Soc. Amer., vol. 99, pp. 1699-1709, 1996.
28. K. Stevens, "On the quantal nature of speech," J. Phonet., vol. 17, pp. 3-45, 1989.
29. J. Sun and L. Deng, "An overlapping-feature based phonological model incorporating linguistic constraints: Applications to speech recognition," J. Acoust. Soc. Amer., vol. 111, no. 2, pp. 1086-1101, Feb. 2002.
30. D. van Bergem, "Acoustic vowel reduction as a function of sentence accent, word stress and word class," Speech Commun., vol. 12, pp. 1-12, 1993.
31. W. Wang, A. Stolcke, and M. Harper, "The use of a linguistically motivated language model in conversational speech recognition," in Proc. IEEE ICASSP, vol. I, May 2004, pp. 261-264.
32. J. Wouters and M. Macon, "Control of spectral dynamics in concatenative speech synthesis," IEEE Trans. Speech Audio Process., vol. 9, no. 1, pp. 30-38, Jan. 2001.
33. J. Zhou, F. Seide, and L. Deng, "Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM," in Proc. IEEE ICASSP, vol. I, Apr. 2003, pp. 744-747.