Patent
1994-03-16
1995-01-10
MacDonald, Allen R.
395 265, G10L 900
Patent
active
053815130
ABSTRACT:
A neural network with a high recognition rate when applied to static patterns is made applicable to dynamic time series patterns such as voice signals. Plural units with one or more inputs and outputs are interconnected, and a unique load coefficient is assigned to each connection to weight the signals flowing through that connection. The neural network includes an input unit group to which are input the components of plural vectors included in the input feature vector series {y(t)}; an output unit which outputs the converted vectors, which are produced by passing the input vectors through each unit and the associated connections; and J paths from input unit group to the output unit group. The units are connected to form a Hidden Markov Model wherein each signal path identified as j=1, 2, . . . , J corresponds to the same state.
REFERENCES:
patent: 4885757 (1989-12-01), Provence
patent: 5228087 (1993-07-01), Bickerton
Chong et al., "Classification and Regression Tree Neural Networks For Automatic Speech Recognition", Inter. Neural Network Conf. INNC 90 Paris, Jul. 9-13, 1990, pp. 187-190.
"Dynamic Neural Network--A New Speech Recognition Model Based On Dynamic Programming and Neural Network", Sakoe et al., NEC Corp. pp. 25-30, 1987.
"Neural Network Driven Hidden Markov Model", Tsuboka, Matsushita Electric Industrial Co., Ltd., pp. 55-62, 1989.
"A Multi-Layered Neural Network With Time Series Processing Ability", Tsuboka et al., Matsushita Electric Industiral Co., Ltd, & Osaka University, pp. 63-70, 1991.
"Speaker-Independent Word Recognition Using A Neural Prediction Model", Iso et al., IEEE 1990, pp. 441-444.
"Neural Predictive Hidden Markov Model", Tsuboka et al., Matsushita Electric Industrial Co., Ltd. & Osaka University, pp. 1341-1344, Nov. 1990.
Doerrler Michelle
MacDonald Allen R.
Matsushita Electric - Industrial Co., Ltd.
LandOfFree
Time series signal analyzer including neural network having path does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Time series signal analyzer including neural network having path, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Time series signal analyzer including neural network having path will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-857283