Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1997-09-15
2000-02-15
Hudspeth, David R.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704255, G10L 506
Patent
active
060263598
ABSTRACT:
A model adaptation scheme in the pattern recognition, which is capable of realizing a fast, real time model adaptation and improving the recognition performance. This model adaptation scheme determines a change in a parameter expressing a condition of pattern recognition and probabilistic model training between an initial condition at a time of acquiring training data used in obtaining a model parameter of each probabilistic model and a current condition at a time of actual recognition. Then, the probabilistic models are adapted by obtaining a model parameter after a condition change by updating a model parameter before a condition change according to the determined change, when the initial condition and the current condition are mismatching. The adaptation processing uses a Taylor expansion expressing a change in the model parameter in terms of a change in the parameter expressing the condition.
REFERENCES:
patent: 5271088 (1993-12-01), Bahler
patent: 5465317 (1995-11-01), Epstein
patent: 5487133 (1996-01-01), Park et al.
patent: 5537647 (1996-07-01), Hermansky et al.
patent: 5566270 (1996-10-01), Albesano et al.
patent: 5627939 (1997-05-01), Huang et al.
patent: 5715367 (1998-02-01), Gillick et al.
patent: 5721808 (1998-02-01), Minami et al.
patent: 5791904 (1998-08-01), Russell et al.
patent: 5799276 (1998-08-01), Komissarchik et al.
Martin, F., et al. "Recognition of Noisy Speech by using the Composition of Hidden Markov Models." pp. 65-66.
Gales, M.J.F., and Young, S. (1992) "An Improved Approach To The Hidden Markov Model Decomposition Of Speech And Noise." pp. I-233-I-236 Cambridge University.
Boll, Steven. (1979) "Suppression of Acoustic Noise in Speech Using Spectral Subtraction," pp. 113-120 IEEE Transactions on Acoustics, Speech, and Signal, Processing vol. ASSP-27, No. 2.
Flaherty et al, "Orthogonal transformations of Stacked Feature Vectors applied to HMM Speech Recognition", IEE 1993, vol. 140, #2, Apr., 19.
Cheng et al, "Improved Model Parameter Compensation Methods for Noise Robust Speech Recognition", IEEE, pp. 561-564, 1998.
Kim, "Statistical Linear Approximation for Environment Compensation", IEEE Signal Processing Letters, vol. 5 #1, pp. 8-10, Jan., 1999.
Hwang et al, "Feature Adaptation Using Deviation Vector for robust speech Recognition in Noisy Environment", 1997 IEEE, pp. 1227-1230.
Moreno et al, "A Vector Taylor Series approach for Environment Independent Speech Recognition", 1995 IEEE, pp. 733-736.
Sagayama Shigeki
Takahashi Jun-Ichi
Takahashi Satoshi
Yamaguchi Yoshikazu
Hudspeth David R.
Nippon Telegraph and Telephone Corporation
Opsasnick Michael N.
LandOfFree
Scheme for model adaptation in pattern recognition based on Tayl does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Scheme for model adaptation in pattern recognition based on Tayl, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Scheme for model adaptation in pattern recognition based on Tayl will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1914251