Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1997-09-26
1999-07-13
Dorvil, Richemond
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704234, 704256, G10L 506
Patent
active
059240660
ABSTRACT:
A system and method for classifying a speech signal within a likely speech signal class of a plurality of speech signal classes are provided. Stochastic models include a plurality of states having state transitions and output probabilities to generate state sequences which model evolutionary characteristics and durational variability of a speech signal. The method includes extracting a frame sequence, and determining a state sequence for each stochastic model with each state sequence having full state segmentation. Representative frames are determined to provide speech signal time normalization. A likely speech signal class is determined from a neural network having a plurality of inputs receiving the representative frames and a plurality of outputs corresponding to the plurality of speech signal classes. An output signal is generated based on the likely stochastic model.
REFERENCES:
patent: 5566270 (1996-10-01), Albesano et al.
patent: 5579436 (1996-11-01), Chou et al.
patent: 5586215 (1996-12-01), Stork et al.
patent: 5596679 (1997-01-01), Wang
patent: 5621857 (1997-04-01), Cole et al.
patent: 5749066 (1998-05-01), Nussbaum
patent: 5758021 (1998-05-01), Hackbarth
patent: 5787387 (1998-07-01), Aguilar
"Real-World Speech Recognition With Neural Networks", by Etienne Barnard et al, Center for Spoken Language Understanding, Oregon Graduate Institute, Portland.
"Phoneme Recognition UsingTime-Delay Neural Networks", by Alexander Waibel, et al, IEEE Transactions on Acoustics, Speech & Signal Processing, vol. 37, No. 3, Mar. 1989.
"Links Between Markov Models And Multilayer Perceptrons", by Herve Bourlard, et al, IEEE Transactions On Pattern Analysis & Machine Intelligence, vol. 12, No. 12, Dec.
"A New Connected Word Recognition Algorithm Based on HMM/L VQ Segmentation And LVQ Classification", by Padma Ramesh et al, IEEE 1991, pp. 113-116.
"Competitive Training: A Connectionist Approach To The Discriminative Training Of Hidden Markov Models",by S.J. Young, IEEE Proceedings--I, vol. 138, No. 1, Feb. 1991.
"Global Optimization Of A Neural Network--Hidden Markov Model Hybrid", by Yoshua Bengio et al, IEEE Transactions on Neural Networks, vol. 3, No. 2, Mar. 1992, pp. 252-.
"A Hybrid Segmental Neural Net/Hidden Markov Model System For Continuous Speech Recognition", by G. Zavaliagkos et al, IEEE Transactions On Speech & Audio Processing, vol.
"Transient Sonar Signal Classification Using Hidden Markov Models And Neural Nets," by Amlan Kundu et al, IEEE Journal of Oceanic Engineering, vol. 19, No. 1, Jan.
"An Integrated Hybrid Neural Network And Hidden Markov Model Classifier For Sonar Signal Classification", by Amlan Kundu et al, 1995 IEEE, pp. 3587-3590.
"Neural Networks For Alphabet Recognition", by Mark Fanty et al, Handbook of Neural Computation, 1997, pp. G1.5:1-G1.5:5.
Dorvil Richemond
MediaOne, Inc.
U S West, Inc.
LandOfFree
System and method for classifying a speech signal does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for classifying a speech signal, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for classifying a speech signal will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2288253