Patent
1996-04-30
1998-05-12
MacDonald, Allen R.
395 255, G10L 506
Patent
active
057519048
ABSTRACT:
A speech recognition system can recognize a plurality of voice data having different patterns. The speech recognition system has a voice recognizing and processing device including a plurality of speech recognition neural networks that have previously learned different voice patterns to recognize given voice data. Each of the speech recognition neutral networks is adapted to judge whether or not input voice data coincides with one of the voice data to be recognized. Each neural network then outputs adaptation judgment data representing the adaptation in speech recognition. A selector responsive to the adaptation judgment data from each of the speech recognition neural networks selects one of the neural networks that has the highest adaptation in speech recognition. An output control device outputs the result of speech recognition from the speech recognition neural network selected by the selector.
REFERENCES:
patent: 3610831 (1971-10-01), Moshier
patent: 5255342 (1993-10-01), Nitta
patent: 5263097 (1993-11-01), Katz et al.
patent: 5307444 (1994-04-01), Tsuboka
patent: 5377305 (1994-12-01), Russo
Interactive Query Learning for Isolated Speech Recognition Hwang et al. Sep. 1992 IEEE.
Phoneme-based Word Recognition by NN--A Step Toward Large Vacab. Recognition. Hirai et al. IEEE/Jun. 1990.
Modularity and Scaling in Large Phonemic Neural Networks Waibel et al. IEEE/Dec. 1989.
Aijaz A. Baloch et al.; "A Neural System for Behavioral Conditioning of Mobile Robots;" IJCNN International Joint Conference on Neural Networks; San Diego, Jun. 17-21, 1990; pp. II-723 to II-728.
Tony Robinson et al.; "A recurrent error propagation network speech recognition system;" 8300 Computer Speech & Language 5(1991) Jul., No. 3, London, GB; pp. 259-274.
Yoshua Bengio et al.; "Learning the dynamic nature of speech with back-propagation for sequences;" 8221 Pattern Recognition Letters 13(1992) May, No. 5, Amsterdam, NL; pp. 375-385.
Takehisa Tanaka; "A Complex Sequence Recognition Model" IJCNN International Joint Conference on Neural Networks, Baltimore, MD, Jun. 7-11, 1992 vol. 4, pp. IV-201-IV-207.
Dorvil Richemond
MacDonald Allen R.
Seiko Epson Corporation
LandOfFree
Speech recognition system using neural networks does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Speech recognition system using neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition system using neural networks will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-992080