Patent
1995-03-29
1997-04-01
MacDonald, Allen R.
395 26, 395 264, G10L 900
Patent
active
056175094
ABSTRACT:
In a statistical based speech recognition system, one of the key issues is the selection of the Hidden Markov Model that best matches a given sequence of feature observations. The problem is usually addressed by the calculation of the maximum likelihood, ML, state sequence by means of a Viterbi or other decoder. Noise or inadequate training can produce a ML sequence associated with a Hidden Markov Model other than the correct model. The method of the present invention provides improved robustness by combining the standard ML state sequence score (416) with an additional path score (418) derived from the dynamics of the ML score as a function of time. These two scores, when combined, form a hybrid metric (420) that, when used with the decoder, optimizes selection of the correct Hidden Markov Model (422).
REFERENCES:
patent: 4348553 (1982-09-01), Baker et al.
patent: 5440662 (1995-08-01), Sukkar
G. David Foney, Jr. "The Viterbi Algorithm", Proc. IEEE, vol. 61, No. 3, Mar. 1973 pp. 268-278.
John S. Bridle, Michael D. Brown, and Richard M. Chamberlain "An Algorithm for Connected Word Recognition," ICASSP '82 pp. 899-902, May 1982.
Lawrence R. Rabiner, "A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition," Proc. IEEE, vol. 77, No. 2 Feb., 1989, pp. 257-286.
Hartman Matthew A.
Kushner William M.
Srenger Edward
MacDonald Allen R.
Motorola Inc.
Sartori Michael A.
Stockley Darleen J.
LandOfFree
Method, apparatus, and radio optimizing Hidden Markov Model spee does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method, apparatus, and radio optimizing Hidden Markov Model spee, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method, apparatus, and radio optimizing Hidden Markov Model spee will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-546496