Patent
1995-05-04
1998-04-07
Knepper, David D.
395 23, 395 253, G10L 900, G10L 506
Patent
active
057374864
ABSTRACT:
A method for training speech sound predictors, which define a reference pattern representative of a reference category, by using training patterns representing speech sound to adjust parameters characterizing each of the predictors. The training patterns may represent a training category identical with the reference category. The training patterns may alternatively represent a training category different from the reference category. The training method includes steps of initializing the parameters; calculating the prediction error between the reference pattern and one of the training patterns at a time; correcting the parameters so as to either decrease the prediction error (according to the first aspect) or increase the prediction error (according to the second aspect), and iterating the second and third steps for all of the training patterns.
REFERENCES:
Deller et al., "Discrete-Time Processing of Speech Signals," 1987, pp. 814-847, Prentice Hall, NJ.
Bourland et al., "Merging Multilayer Perceptions and Hidden Markov Models: Some Experiments in Continuous Speech Recognition", Jul. 1989, ISI, pp. 1-18.
Lippmann, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
Knepper David D.
NEC Corporation
LandOfFree
Pattern recognition method by using reference patterns each of w 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 recognition method by using reference patterns each of w, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern recognition method by using reference patterns each of w will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-21656