Electrical audio signal processing systems and devices – One-way audio signal program distribution – Public address system
Patent
1985-01-31
1988-04-26
Kemeny, Emanuel S.
Electrical audio signal processing systems and devices
One-way audio signal program distribution
Public address system
G10L 500
Patent
active
047410361
ABSTRACT:
In a speech recognition system, discrimination between similar-sounding uttered words is improved by weighting the probability vector data stored for the Markov model representing the reference word sequence of phones. The weighting vector is derived for each reference word by comparing similar sounding utterances using Viterbi alignment and multivariate analysis which maximizes the differences between correct and incorrect recognition multivariate distributions.
REFERENCES:
patent: 4099257 (1978-06-01), Arnold et al.
patent: 4100370 (1978-07-01), Suzuki et al.
Language and Speech, vol. 4, No. 4, Oct./Dec. 1961, pp. 200-219; G. E. Peterson: "Automatic Speech Recognition Procedures".
The Bell System Technical Journal, vol. 60, No. 5, May-Jun. 1981, pp. 739-766, American Telephone and Telegraph Co., Murray Hill, NJ, US; L. R. Rabiner et al.: "A Two-Pass Pattern-Recognition Approach to Isolated Word Recognition".
Bahl Lalit R.
deSouza Peter V.
Mercer Robert L.
Block Marc A.
International Business Machines - Corporation
Kemeny Emanuel S.
LandOfFree
Determination of phone weights for markov models in a speech rec does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Determination of phone weights for markov models in a speech rec, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Determination of phone weights for markov models in a speech rec will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-825292