Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1997-09-11
1999-12-28
Hudspeth, David R.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704245, G10L 708
Patent
active
060093900
ABSTRACT:
In a speech recognition system, tied-mixture hidden Markov models (HMMs) are used to match, in the maximum likelihood sense, the phonemes of spoken words given the acoustic input thereof. In a well known manner, such speech recognition requires computation of state observation likelihoods (SOLs). Because of the use of HMMs, each SOL computation involves a substantial number of Gaussian kernels and mixture component weights. In accordance with the invention, the number of Gaussian kernels is cut down to reduce the computational complexity and increase the efficiency of memory access to the kernels. For example, only the non-zero mixture component weights and the Gaussian kernels associated therewith are considered in the SOL computation. In accordance with an aspect of the invention, only a subset of the Gaussian kernels of significant values, regardless of the values of the associated mixture component weights, are considered in the SOL computation. In accordance with another aspect of the invention, at least some of the mixture component weights are quantized to reduce memory space needed to store them. As such, the computational complexity and memory access efficiency are further improved.
REFERENCES:
patent: 5473728 (1995-12-01), Luginbuhl et al.
patent: 5794198 (1998-08-01), Takahashi et al.
patent: 5825978 (1998-10-01), Digalakis et al.
Digalakis, V.V.; Rtischev, D.; Neumeyer, L.G., "Speaker adaptation using constrained estimation of Gaussian mixtures," Speech and Audio Processing, IEEE Transactions on, vol. 3, No. 5, Sep. 1995, pp. 357-366.
Digalakis, V.V.; Monaco, P.; and Murveit, H., "Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers," Speech and Audio Processing, IEEE Transactions on, vol. 4 4, pp. 281-289, Jul. 1996.
J. R. Bellegarda et al., "Tied Mixture Continuous Parameter Modeling for Speech Recognition," IEEE Trans. Acoustics Speech Signal Process., vol. 38, No. 12, 1990, pp. 2033-2045.
X. D. Huang et al., "Semi-Continuous Hidden Markov Models for Speech Signals," Computer Speech and Language, vol. 3, 1989, pp. 239-251.
E. Bocchieri, "A study of the Beam-Search Algorithm for Large Vocabulary Continuous Speech Recognition and Methods for Improved Efficiency," Proceedings Eurospeech, 1993, pp. 1521-1524.
Y. Linde et al., "An Algorithm for Vector Quantizer Design," IEEE Trans. Communications, vol. COM-28, Jan. 1980, pp. 84-95.
E. Bocchieri, "Vector Quantization for the Efficient Computation of Continuous Density Likelihoods," IEEE, 1993, pp. II 692-695.
P. Lockwood et al., "Experiments with a Non-Linear Spectral Subtractor (NSS), Hidden Markov Models and the Projection, for Robust Speech Recognition in Cars," Proceedings Eurospeech, 1993, pp. 79-82.
Gupta Sunil K.
Haimi-Cohen Raziel
Soong Frank K.
Hudspeth David R.
Lucent Technologies - Inc.
Storm Donald L.
LandOfFree
Technique for selective use of Gaussian kernels and mixture comp does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Technique for selective use of Gaussian kernels and mixture comp, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Technique for selective use of Gaussian kernels and mixture comp will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2389474