Temporally varying weight regression: A semi-parametric trajectory model for automatic speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 22, Issue 1, 2014, Pages 151-160

  Liu, Shilin ^a   Sim, Khe Chai ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Acoustic modeling; Hidden markov model; Pattern recognition; Trajectory modeling

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; HIDDEN MARKOV MODELS; PATTERN RECOGNITION; TRAJECTORIES; GAUSSIAN DISTRIBUTION; MARKOV PROCESSES; MAXIMUM LIKELIHOOD; MAXIMUM LIKELIHOOD ESTIMATION; OBJECT RECOGNITION; PARAMETER ESTIMATION; SPEECH; TRELLIS CODES;

ACOUSTIC MODEL; AUTOMATIC SPEECH RECOGNITION; GAUSSIAN MIXTURE MODEL; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; NOISY SPEECH RECOGNITION; STATE-OF-THE-ART SYSTEM; TRAJECTORY MODELING; VOCABULARY RECOGNITION;

OBJECT RECOGNITION; SPEECH RECOGNITION;

EID: 84897953008     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASLP.2013.2285487     Document Type: Article

References (29)

1. L. Rabiner, "A tutorial on hiddenMarkov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, Feb. 1989.
2. B. Juang, S. Levinson, and M. Sondhi, "Maximum likelihood estimation for multivariate mixture observations of Markov chains," IEEE Trans. Inf. Theory, vol. IT-32, no. 2, pp. 307-309, Mar. 1986. (Pubitemid 16613645)
3. A.-V. Rosti and M. Gales, "Switching linear dynamical systems for speech recognition," 2003, Tech. Rep.
4. M. Ostendorf and S. Roukos, "A stochastic segment model for phoneme-based continuous speech recognition," IEEE Trans. Acoust., Speech Signal Process., vol. 37, no. 12, pp. 1857-1869, Dec. 1989. (Pubitemid 20642698)
5. M. Ostendorf, V. Digalakis, and O. A. Kimball, "From HMMs 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. 1995. (Pubitemid 126753024)
6. A.-V. Rosti and M. Gales, "Factor analysed hiddenMarkov models for speech recognition," Comput. Speech Lang., pp. 181-200, 2004.
7. H. Gish and K. Ng, "Parametric trajectory models for speech recognition,"in Proc. ICSLP, 1996, vol. 1, pp. 466-469.
8. L. Deng, X. Li, D. Yu, and A. Acero, "A hidden trajectory model with bi-directional target-filtering: Cascaded vs. integrated implementation for phonetic recognition," in Proc. ICASSP, 2005, pp. 337-340.
9. J. Bilmes, "Buried Markov models for speech recognition," in Proc. ICASSP, 1999, vol. 2, pp. 713-716.
10. K. Tokuda, H. Zen, and T. Kitamura, "Trajectory modeling based on hmms with the explicit relationship between static and dynamic features,"in Proc. Eurospeech, 2003, pp. 865-868.
11. K. Tokuda, H. Zen, and T. Kitamura, "Reformulating the HMM as a trajectory model," in Proc. Beyond HMM Workshop, 2004.
12. S. Young, "A review of large-vocabulary continuous-speech recognition,"IEEE Signal Process. Mag., vol. 13, no. 5, p. 45, 1996.
13. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "FMPE: Discriminatively trained features for speech recognition," in Proc. ICASSP, 2005, vol. 1, pp. 961-964.
14. B. Zhang, S. Matsoukas, and R. Schwartz, "Discriminatively trained region dependent feature transforms for speech recognition," in Proc. ICASSP, 2006, vol. 1, pp. 313-316.
15. K. Sim and M. Gales, "Discriminative semi-parametric trajectory model for speech recognition," Comput. Speech Lang., vol. 21, no. 4, pp. 669-687, 2007. (Pubitemid 46880192)
16. S. Liu and K. Sim, "Implicit Trajectory Modelling Using Temporally Varying Weight Regression for Automatic Speech Recognition," in Proc. ICASSP, 2012, pp. 4761-4764.
17. A. Wächter and L. Biegler, "On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming,"Math. Program., vol. 106, no. 1, pp. 25-57, 2006. (Pubitemid 41813168)
18. R. Haeb-Umbach and H. Ney, "Linear discriminant analysis for improved large vocabulary continuous speech recognition," in Proc. ICASSP, 1992, vol. 1, pp. 13-16.
19. K. Sim and S. Liu, "Semi-parametric trajectory modeling using temporally varying feature mapping for speech recognition," in Proc. Interspeech, 2010, pp. 2982-2985.
20. Q. Zhu, B. Chen, N. Morgan, and A. Stolcke, "On using MLP features in LVCSR," in Proc. ICSLP, 2004.
21. C. Wellekens, "Explicit time correlation in hidden Markov models for speech recognition," in Proc. ICASSP, 1987, pp. 384-386.
22. P. Woodland, "Hidden Markov models using vector linear prediction and discriminative output distributions," in Proc. ICASSP, 1992, pp. 509-512.
23. D. Povey and P. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002, vol. 1, pp. I-105.
24. D. Povey, "Discriminative training for large vocabulary speech recognition,"Ph.D. dissertation, Cambridge Univ., Cambridge, U.K., 2004.
25. S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, and D. Povey et al., The HTK book (for HTK version 3.4), 2006.
26. N. Parihar and J. Picone, "Performance analysis of the Aurora large vocabulary baseline system," in Proc. Eur. Signal Process. Conf., 2004.
27. Y. Wang and M. J. Gales, "Speaker and noise factorization for robust speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 20, no. 7, pp. 2149-2158, Sep. 2012.
28. E. standard doc, "Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced frontend feature extraction algorithm; compression algorithms," Tech. Rep., 2003.
29. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus among words: Lattice-based word error minimization," in Proc. Eurospeech, 1999, vol. 99, pp. 495-498.