Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2005-03-17
2010-02-16
Opsasnick, Michael N (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
Reexamination Certificate
active
07664642
ABSTRACT:
A probabilistic framework for acoustic-phonetic automatic speech recognition organizes a set of phonetic features into a hierarchy consisting of a broad manner feature sub-hierarchy and a fine phonetic feature sub-hierarchy. Each phonetic feature of said hierarchy corresponds to a set of acoustic correlates and each broad manner feature of said broad manner feature sub-hierarchy is further associated with a corresponding set of acoustic landmarks. A pattern recognizer is trained from a knowledge base of phonetic features and corresponding acoustic correlates. Acoustic correlates are extracted from a speech signal and are presented to the pattern recognizer. Acoustic landmarks are identified and located from broad manner classes classified by the pattern recognizer. Fine phonetic features are determined by the pattern recognizer at and around the acoustic landmarks. The determination of fine phonetic features may be constrained by a pronunciation model. The most probable feature bundles corresponding to words and sentences are those that maximize the joint a posteriori probability of the fine phonetic features and corresponding acoustic landmarks. When the hierarchy is organized as a binary tree, binary classifiers such as Support Vector Machines can be used in the pattern classifier and the outputs thereof can be converted probability measures which, in turn may be used in the computation of the aforementioned joint probability of fine phonetic features and corresponding landmarks.
REFERENCES:
patent: 4813076 (1989-03-01), Miller
patent: 4820059 (1989-04-01), Miller et al.
patent: 5715367 (1998-02-01), Gillick et al.
patent: 5749069 (1998-05-01), Komori et al.
patent: 5805771 (1998-09-01), Muthusamy et al.
patent: 5822729 (1998-10-01), Glass
patent: 5848388 (1998-12-01), Power et al.
patent: 5864809 (1999-01-01), Suzuki
patent: 5893058 (1999-04-01), Kosaka
patent: 5953701 (1999-09-01), Neti et al.
patent: 6076053 (2000-06-01), Juang et al.
patent: 6208963 (2001-03-01), Martinez et al.
patent: 7457745 (2008-11-01), Kadambe et al.
Zue, V., et al., “Acoustic segmentation and phonetic classificaion in the SUMMIT system,” Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (Glasgow), pp. 389-392, May 1989.
Bitar, N., et al., “Knowledge-Based Parameters for HMM Speech Recognition”, The 1996 IEEE Conference on Acoustics, Speech and Signal Processing, pp. 29-32, 1996.
Juneja, A., et al., “Segmentation of continuous speech using acoustic-phonetic parameters and statistical learning”, Proceedings of International Conference on Neural Information Processing, vol. 2, p. 726-730, 2002.
Shah, J., et al., “Robust Voiced/Unvoiced Classification Using Novel Features and Gaussian Mixture Model”, IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP), Montreal, Canada, May 17-21, 2004, http://shahj.net/publications/icassp03—shah.pdf.
Juneja, A., et al., “Speech Segmentation Using Probabilistic Phonetic Feature Hierarchy and Support Vector Machines”, Proceedings of International Joint Conference on Neural Networks, Portland, Oregan, 2003, http://www.enee.umd.edu/˜juneja/paper—ijcnn.pdf or http//www.isr.umd.edu/Labs/SCL/publications/Amit—ijcnn—2003.pdf.
Glass, J., et al., “A probabilistic framework for feature-based speech recognition”, International Conference on Spoken Language Processing, pp. 2277-2280, 1996.
Stevens, K., “Toward a model for lexical access based on acoustic landmarks and distinctive features”, J. Acoust. Soc. Am., 111(4), 1872-1891, 2002.
Glass, J., et al., “Multi-level acoustic segmentation of continuous speech”, International Conference on Acoustics, Speech and Signal Processing, New York, NY, pp. 429-432, 1988.
Drish, J., “Obtaining calibrated probability estimates from support vector machines”, Final project for CSE 254: Seminar on Learning Algorithms, University of Califomia, San Diego, Jun. 2001, http://www-cse.ucsd.edu/users/jdrish/svm.pdf.
Espy-Wilson Carol
Juneja Amit
Opsasnick Michael N
Rosenberg , Klein & Lee
University of Maryland
LandOfFree
System and method for automatic speech recognition from... 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 automatic speech recognition from..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for automatic speech recognition from... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4207693