Construction of state-dependent dynamic parameters using the maximum likelihood approach: Applications to speech recognition

Signal Processing

Volumn 55, Issue 2, 1996, Pages 149-165

  Deng, L ^a   Rathinavelu, C ^a  

^a UNIVERSITY OF WATERLOO   (Canada)

Author keywords

Delta cepstrum; EM algorithm; Hidden markov model; Linear and nonlinear systems; Speech signal

Indexed keywords

DYNAMIC PROGRAMMING; LEARNING ALGORITHMS; MARKOV PROCESSES; OPTIMIZATION; PARAMETER ESTIMATION; SPEECH ANALYSIS; SPEECH TRANSMISSION; TIME VARYING SYSTEMS;

DELTA PARAMETER TECHNIQUE; DYNAMIC PARAMETERS;

SPEECH RECOGNITION;

EID: 0030419718     PISSN: 01651684     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0165-1684(96)00127-2     Document Type: Article

References (21)

1. T. Applebaum and B. Hanson, "Regression features for recognition of speech in quiet and in noise", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Vol. 2, 1991, pp. 985-988.
2. L.E. Baum, "An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes", Inequalities, Vol. 3, 1972, pp. 1-8.
3. P. Brown, The acoustic modeling problem in automatic speech recognition, Technical Report RC 12750, IBM Thomas J. Watson Research Center, 1987.
4. Y. Chow et al., "BYBLOS: the BBN continuous speech recognition system", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., 1987, pp. 89-92.
5. Chris Woodford, "Solving linear and non-linear equations", Ellis Horwood Limited, Chichester, UK, 1992, pp. 164-176.
6. L. Deng, "Integrated optimization of dynamic feature parameters for hidden Markov modeling of speech", IEEE Signal Process., Lett., Vol. 1, No. 4, 1994, pp. 66-69.
7. L. Deng, P. Kenny, M. Lennig, V. Gupta, F. Seitz and P. Mermelstein, "Phonemic hidden Markov models with continuous mixture output densities for large vocabulary word recognition", IEEE Trans. Acoust. Speech Signal Process., Vol. 39, No. 7, July 1991, pp. 1677-1681.
8. L. Deng, M. Lennig, F. Seitz and P. Mermelstein, "Large vocabulary word recognition using context-dependent allophonic hidden Markov models", Computer Speech and Language, Vol. 4, 1990, pp. 345-357.
9. S. Furui, "Speaker independent isolated word recognition using dynamic features of speech spectrum", IEEE Trans. Acoust. Speech Signal Process., Vol. 34, 1986, pp. 52-59.
10. P.E. Gill, W. Murray and M.H. Wright, Practical Optimization, Academic Press, New York, 1981.
11. V. Gupta, M. Lennig and P. Mermelstein, "Integration of acoustic information in a large vocabulary word recognizer", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., pp. 697-700.
12. R. Haeb-Umbach, D. Geller and H. Ney, "Improvements in connected digit recognition using linear discriminant analysis and mixture densities", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Vol. 2, 1993, pp. 239-242.
13. X. Huang, F. Alleva, H. Hon. M. Hwang, K. Lee and R. Rosenfeld, "The SPHINX-II speech recognition system: an overview", Computer Speech Language, Vol. 7, No. 2, 1993, pp. 137-148.
14. M.J. Hunt, D.C. Bateman, S.M. Richarson and P. Piau, "An investigation of PLP and IMELDA acoustic representation and of their potential combination", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Vol. 2, 1991, pp. 881-884.
15. K. Lee and H. Hon, "Context-dependent phonetic hidden Markov models for continuous speech recognition", IEEE Trans. Acoust. Speech Signal Process., Vol.38, No.4, April 1990, pp. 599-609.
16. C. Lee, L. Rabiner, R. Pieraccini and J. Wilpon, "Acoustic modeling for large vocabulary speech recognition", Computer Speech and Language, Vol. 4, 1990, pp. 127-165.
17. H. Leung, B. Chigier and G. Glass, "A comparative study of signal representations and classification techniques for speech recognition", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., 1993, pp. 680-683.
18. A. Ljolje, "High accuracy phone recognition using context clustering and quasi-triphonic models", Computer Speech and Language, Vol. 8, 1994, pp. 129-151.
19. W.H. Press, B.P. Flannery, S.A. Teukolsky and W.T. Vetterling, Numerical Recipes - The Art of Scientific Computing, Cambridge University Press, Cambridge, 1989, pp. 269-273.
20. L. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition", IEEE Proc., Vol. 77, 1989, pp. 257-285.
21. P. Woodland, J. Odell, V. Valtchev and S. Young, "Large vocabulary continuous speech recognition using HTK", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Vol. 1, 1994.