Patent
1997-03-19
1998-04-28
MacDonald, Allen R.
395 263, G10L 504
Patent
active
057456496
ABSTRACT:
For speech recognition systems a method for modeling context-dependent phonetic categories using artificial neural nets has been described. First, linguistically motivated context-clustering is employed to reduce the number of context-dependent categories. Second, phone-specific MLP structures are used where the number of outputs in each MLP is based on the number of left and right contexts occurring in a training database. The structure of each MLP can be automatically determined using the cascade-correlation learning algorithm.
REFERENCES:
patent: 4975961 (1990-12-01), Sakoe
patent: 4977599 (1990-12-01), Bahl et al.
patent: 5040215 (1991-08-01), Amano et al.
patent: 5075896 (1991-12-01), Wilcox et al.
patent: 5109418 (1992-04-01), Van Hemert
patent: 5131043 (1992-07-01), Fujii et al.
patent: 5140668 (1992-08-01), Hattori
patent: 5146593 (1992-09-01), Brandle et al.
patent: 5165095 (1992-11-01), Borcherding
patent: 5170432 (1992-12-01), Hackbarth et al.
patent: 5228087 (1993-07-01), Bickerton
patent: 5233681 (1993-08-01), Bahl et al.
patent: 5263117 (1993-11-01), Nadas et al.
patent: 5278942 (1994-01-01), Bahl et al.
patent: 5317673 (1994-05-01), Cohen et al.
patent: 5404422 (1995-04-01), Sajamoto et al.
patent: 5410635 (1995-04-01), Sakoe
patent: 5457770 (1995-10-01), Miyazawa
IEEE international conference on neural networks, Rossen et al., "Training methods for a connectionist model of consonant-vowel syllable recognition", pp. 239-246 vol. 1, Jul. 1988.
COMSIG 1989, Van der Merwe et al., "Back-propagation Networks for phoneme recognition", pp. 143-148, Jun. 1989.
Austin, S., Zavaliagkos, G., Makhoul, J., and Schwartz, R., "Speech Recognition Using Segmental Neural Nets," ICASSP-92, San Francisco, CA, Mar. 1992, pp. I-625-629.
Chigier, B., and Leung, H.C., "The Effects of Signal Representations, Phonetic Classification Techniques, and The Telephone Network," ICSLP-92, Banff, Canada, Oct. 1992, pp. 97-100.
Fahlman, S.E., and Labiere, C., "The Cascade-Correlation Learning Architecture". Carnegie-Mellon University, Computer Science Dept., Ref. No. CMU-CS-90-100, Feb. 1990.
Hon, H., "Vocabulary-Independent Speech Recognition: the VOCIND system," P.h.D Thesis, Carnegie-Mellon University, Mar. 1992.
Jankowski, C., Kalyanswamy, A., Basson, S., and Spitz, J., "NTIMIT: A Phonetically Balanced, Continuous Sppech, Telephone Bandwidth Speech Database," ICASSP-90, Albuquerque, NM, Apr. 1990, pp. 109-112.
Lee, K., "Large-Vocabulary Speaker-Independent Continuous Speech Recognition: the SPHINX system," P.h.D Thesis, Carnegie-Mellon University, Apr. 1988.
Leung, H.C., Hetherington, L.I., and Zue, V., "Speech Recognition Using Stochastic Segment Neural Networks," ICASSP-92, San Francisco, CA, Mar. 1992, pp. I-613-616.
Lucke, H.; Fallside "Expanding the Vocabulary Of A Connectionist Recognizer Trained On The Darpa Resource Management Corpus," IEEE-92 Cambridge University Engineering Dept., UK, Sep. 1992, pp. I-605-608.
Allen, J; "A Perspective on Man-Machine Communication by Speech," Proceedings of the IEEE, vol. 73, No. 11, Nov. 1985; pp. 1541-1550.
Graff, D.E.; Lynch, T.E.; "Acoustic Phonetic Techniques For Future Automatic Speech Recognition Systems," RCA Engineer 31-1, Jan./Feb. 19, pp. 4-10.
Raj Reddy, D. "Speech Recognition by Machine: A Review," Originally appeared in IEEE Proceedings 64(4):502-531, Apr. 1976.
Lea, Wayne A., Speech Communication Research Laboratory "The Value Of Speech Recognition Systems," Originally appeared in Trends In Speech recognition, pp. 3-18, Speech Science Publications (1986).
Dorvil Richemond
MacDonald Allen R.
Michaelson Peter L.
NYNEX Science & Technology Corporation
Straub Michael P.
LandOfFree
Automated speech recognition using a plurality of different mult does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Automated speech recognition using a plurality of different mult, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated speech recognition using a plurality of different mult will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1541313