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

Abstract We present in this paper an integrated view on the speech preprocessing and speech modeling problems in the design of a hidden Markov model (HMM) based speech recognizer. The integrated model we developed in this study generalizes the conventional, currently widely used delta-parameter technique, which has been confined strictly to the preprocessing domain only, in two significant ways. First, the new model contains state-dependent weighting functions responsible for transforming static speech features into the dynamic ones in a slowly time-varying manner. Second, a novel maximum-likelihood based learning algorithm is developed for the model that allows joint optimization of the state-dependent weighting functions and the remaining conventional HMM parameters. The experimental results obtained from a standard TIMIT phonetic classification task provide preliminary evidence for the effectiveness of our new, general approach to the use of the dynamic characteristics of speech spectra. The results demonstrate that the new approach is most effective for discrimination of stop consonants exhibiting the fastest and most conspicuous dynamic patterns.

[1]  John Makhoul,et al.  BYBLOS: The BBN continuous speech recognition system , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Sadaoki Furui,et al.  Speaker-independent isolated word recognition using dynamic features of speech spectrum , 1986, IEEE Trans. Acoust. Speech Signal Process..

[3]  Steve J. Young,et al.  Large vocabulary continuous speech recognition using HTK , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  L. Baum,et al.  An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process , 1972 .

[5]  Philip E. Gill,et al.  Practical optimization , 1981 .

[6]  Li Deng,et al.  Large vocabulary word recognition using context-dependent allophonic hidden Markov models☆ , 1990 .

[7]  James R. Glass,et al.  A comparative study of signal representations and classification techniques for speech recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Alan G. Williamson,et al.  Solving linear and non-linear equations , 1994 .

[9]  Patrick Kenny,et al.  Phonemic hidden Markov models with continuous mixture output densities for large vocabulary word recognition , 1991, IEEE Trans. Signal Process..

[10]  W. Press,et al.  Numerical Recipes: The Art of Scientific Computing , 1987 .

[11]  Andrej Ljolje,et al.  High accuracy phone recognition using context clustering and quasi-triphonic models , 1994, Comput. Speech Lang..

[12]  Peter F. Brown,et al.  The acoustic-modeling problem in automatic speech recognition , 1987 .

[13]  Brian Hanson,et al.  Regression features for recognition of speech in quiet and in noise , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[14]  Li Deng.  Integrated optimization of dynamic feature parameters for hidden Markov modeling of speech , 1994, IEEE Signal Process. Lett..

[15]  Chin-Hui Lee,et al.  Acoustic modeling for large vocabulary speech recognition , 1990 .

[16]  Dieter Geller,et al.  Improvements in connected digit recognition using linear discriminant analysis and mixture densities , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[17]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[18]  Mei-Yuh Hwang,et al.  The SPHINX-II speech recognition system: an overview , 1993, Comput. Speech Lang..

[19]  Vishwa Gupta,et al.  Integration of acoustic information in a large vocabulary word recognizer , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.