Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2005-02-01
2005-02-01
Abebe, Daniel (Department: 2655)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S250000
Reexamination Certificate
active
06850888
ABSTRACT:
A method and apparatus are disclosed for training a pattern recognition system, such as a speech recognition system, using an improved objective function. The concept of rank likelihood, previously applied only to the decding process, is applied in a novel manner to the parameter estimation of the training phase of a pattern recognition system. The disclosed objective function is based on a pseudo-rank likelihood that not only maximizes the likelihood of an observation for the correct class, but also minimizes the likelihoods of the observation for all other classes, such that the discrimination between classes is maximized. A training process is disclosed that utilizes the pseudo-rank likelihood objective function to identify model parameters that will result in a pattern recognizer with the lowest possible recognition error rate. The discrete nature of the rank-based rank likelihood objective function is transformed to allow the parameter estimations to be optimized during the training phase.
REFERENCES:
patent: 4587670 (1986-05-01), Levinson et al.
patent: 5579436 (1996-11-01), Chou et al.
patent: 5950158 (1999-09-01), Wang
patent: 5963902 (1999-10-01), Wang
patent: 5963906 (1999-10-01), Turin
patent: 6044344 (2000-03-01), Kanevsky
patent: 6246980 (2001-06-01), Glorion et al.
patent: 6493667 (2002-12-01), de Souza et al.
Bahl et al., “Estimating Hidden Markov Model Parameters So As To Maximize Speech Recognition Accuracy,” IEEE Transactions on Speech and Audio Processing, vol. 1, No. 1, Jan. 1993, 77-83.
Chou et al., “Minimum Error Rate Training Based on N-Best String Models,” II-652-II-655 (1993 IEEE).
Normandin et al., “High-Performance Connected Digit Recognition Using Maximum Mutual Information Estimation,” 299-311 (1994 IEEE).
Bahl et al., “Discriminative Training of Gaussian Mixture Models for Large Vocabulary Speech Recognition Systems,” 613-616 (1996 IEEE).
Valtchev et al., “Lattice-Based Discriminative Training for Large Vocabulary Speech Recognition,” 605-612 (1996 IEEE).
Woodland et al., “Large Scale Discrimination Training for Speech Recognition,” Cambridge University Engineering Department, Cambridge, CB2 1PZ, UK, 7-15 (ASR2000).
Povey et al., “Frame Discrimination Training of HMMs for Large Vocabulary Speech Recognition,” Cambridge University Engineering Department, Cambridge, CB2 1PZ, UK, 1-13.
Gelin-Huet et al., “The Deterministic Annealing Approach for Discriminative Continuous HMM Design,” Signal Compression Lab, Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA.
Gao Yuqing
Li Yongxin
Picheny Michael Alan
Abebe Daniel
Dang, Esq. Thu Ann
Ryan & Mason & Lewis, LLP
LandOfFree
Methods and apparatus for training a pattern recognition... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Methods and apparatus for training a pattern recognition..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods and apparatus for training a pattern recognition... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3449892