Discriminative training of language models for text and...

Details Discriminative training of language models for text and... Discriminative training of language models for text and...

2008-05-27

2008-05-27

Dorvil, Richemond (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S009000, C704S240000

Reexamination Certificate

active

07379867

ABSTRACT:
Methods are disclosed for estimating language models such that the conditional likelihood of a class given a word string, which is very well correlated with classification accuracy, is maximized. The methods comprise tuning statistical language model parameters jointly for all classes such that a classifier discriminates between the correct class and the incorrect ones for a given training sentence or utterance. Specific embodiments of the present invention pertain to implementation of the rational function growth transform in the context of a discriminative training technique for n-gram classifiers.

REFERENCES:
patent: 5467425 (1995-11-01), Lau et al.
patent: 6157912 (2000-12-01), Kneser et al.
P.C. Woodland et al, “Large Scale Discriminative Training for Speech Recognition”, In: Proceedings of ISCA ITRW ASR 2000, pp. 7-16, 2000.
Warnke et al, “Discriminative estimation of interpolation parameteres for language model classifiers”, IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 1, Mar. 15-19, 1999.
European Search Report.
Chelba, C.; and Acero, A.; “Speech Utterance Classification,” Microsoft Research, Jun. 4, 2003, pp. 1-4.
Hong-Kwang Jeff Kuo et al., “Discriminative Training of Language Models for Speech Recognition,” IEEE Transactions, 2002, pp. 325-328.
Chelba, C.; and Acero, A.; “Discriminative Training of N-gram Classifiers for Speech and Text Routing,” Microsoft Research, Sep. 2003, pp. 1-4.
Douglas B. Paul et al., “On the Interaction Between True Source, Training, and Testing Language Models,” IEEE Transactions 1991, pp. 569-572.
Frederick Jelinek and Robert Mercer, “Interpolated estimation of Markov source parameters from sparse data,”Pattern Recognition in Practice, E. Gelsema and L. Kanal, Ed., pp. 381-397. 1980.
Gopalakrishnan, P.S. et al., “An Inequality for Rational Functions With Applications to Some Statistical Estimation Problems,” IEEE Transactions on Information Theory, vol. 37, No. 1, pp. 107-113 (Jan. 1991).

Affiliated with

Also associated with

Rating

Discriminative training of language models for text and... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Discriminative training of language models for text and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Discriminative training of language models for text and... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2798488