Patent
1991-03-21
1994-02-22
Fleming, Michael R.
G10L 902
Patent
active
052895629
ABSTRACT:
Disclosed is an Hidden Markov Model (HMM) training apparatus in which a capacity for discriminating between models is taken into consideration so as to allow a high level of recognition accuracy to be obtained. A probability of a vector sequence appearing from HMMs is computed with respect to an input vector and continuous mixture density HMMs. Through this computation, the nearest different-category HMM, with which the maximum probability is obtained and which belongs to a category different from that of a training vector sequence of a known category, is selected. The respective central vectors of continuous densities constituting the output probability densities of the same-category HMM belonging to the same category as that of the training vector sequence and the nearest different-category HMM are moved on the basis of the vector sequence.
REFERENCES:
patent: 4783804 (1988-11-01), Juang et al.
Frederick Jelinek, "Continuous Speech Recognition by Statistical Methods", Proceedings of the IEEE, vol. 64, No. 4, Apr. 1976, pp. 532-556.
L. R. Rabiner et al., "Some Properties of Continuous Hidden Markov Model Representations", AT&T Technical Journal, vol. 64, No. 6, Jul.-Aug. 1985, pp. 1251-1270.
L. R. Bahl et al., "Speech Recognition with Continuous-Parameter Hidden Markov Models,", 1988 IEEE, pp. 40-43.
L. R. Rabiner et al, "Recognition of Isolated Digits Using Hidden Markov Models with Continuous Mixture," AT&T Technical Journal, vol. 64, No. 6, 1985, pp. 1211-1234.
L. R. Bahl et al, "A New Algorithm for the Estimation of Hidden Markov Model Parameters," Proc. IEEE ICASSP 88, pp. 493-496.
Seiichi Nakagawa, "Speech Regcognition by Probability Models," The Institute of Electornics, Information and Communication Engineers (Jul. 1, 1985), pp. 26-28, 33-42, 44-46, 55-61.
Mizuta Shinobu
Nakajima Kunio
Doerrler Michelle
Fleming Michael R.
Mitsubishi Denki & Kabushiki Kaisha
LandOfFree
Pattern representation model training apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Pattern representation model training apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern representation model training apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-178081