Hidden conditional random field models for phonetic...

Details Hidden conditional random field models for phonetic... Hidden conditional random field models for phonetic...

2004-10-15

2009-12-01

Dorvil, Richemond (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S256000, C704S256100, C704S256200

Reexamination Certificate

active

07627473

ABSTRACT:
A method and apparatus are provided for training and using a hidden conditional random field model for speech recognition and phonetic classification. The hidden conditional random field model uses feature functions, at least one of which is based on a hidden state in a phonetic unit. Values for the feature functions are determined from a segment of speech, and these values are used to identify a phonetic unit for the segment of speech.

REFERENCES:
patent: 2003/0097266 (2003-05-01), Acero
Young, “Acoustic modelling for large vocabulary continuous speech recognition,” Proc. NATO Advanced Study Institute, Edited by Keith Ponting, Published by Springer-Verlag, 1999.
Goodman, “Reduction of maximum entropy models to Hidden Markov Models,”, UAI 2002.
Rabiner, “A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition”, Proc. of the IEEE, vol. 77, Feb. 1989.
J. Lafferty et al., “Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data,” in ICML, pp. 282-289, 2001.
A. McCallum, “Efficiently Inducing Features of Conditional Random Fields,” Inc UAI, 2003.
F. Sha et al., “Shallow Parsing with Conditional Random Fields,” in Proc. HLT- NAACL, 2003.
P.S. Gopalakrishnan, Dimitri Kanevsky, Arthur Nadas, and David Nahamoo, An Inequality for Rational Functions with Applications to Some Statistical Estimation Problems, IEEE Trans. Inf. Thry., 37(1):107-113, Jan. 1991.
Biing-Hwang Juang and Shigeru Katagiri, “Discriminative Learning for Minimum Error Classification,” IEEE Trans. Sig. Proc., 40(12):3043-3054, Dec. 1992.
J.N. Darroch and D. Ratcliff, Generalized Iterative Scaling for Log-Linear Models,: Ann. Math. Stat., 43(5):1470-1480, 1972.
S. Wang, R. Rosenfeld, Y. Zhao, and D. Shuurmans, “The Latent Maximum Entropy Principle,” in IEEE Int. Symp. Inf. Thry., 2002.
C.F. Jeff Wu, “On the Convergence Properties of the EM Algorithm,” Ann. Stat., 11(1):95-103, 1983.
Ruslan Salakhutdinov et al, “Optimization with EM and Expectation-Conjugate-Gradient,” in ICML, 2003.
Wolfgang Macherey et al., “A Comparative Study on Maximum Entropy and Discriminative Training for Acoustic Modeling in Automatic Speech Recognition,” in Eurospeech, pp. 493-496, 2003.
Rathinavelu Chengalvarayan and Li Deng, “HMM-based Speech Recognition Using State-Dependent, Discriminatively Derived Transforms on Mel-Warped DFT Features,” IEEE Trans. Spch. & Aud. Proc., 5(3):243-256, May 1997.
S. Kakade et al., “An Alternate Objective Function for Markovian Fields,” In ICML, 2002.
Hong-Kwang et al., “Maximum Entropy Direct Models for Speech Recognition,” in ASURA, 2003.
Stanley F. Chen et al., “A Guassian Prior for Smoothing Maximum Entropy Models,” Technical Report CMU-CS-99-108, Computer Science Department, Carnegie Mellon University, 1999.
European Search Report from Appln No. 05108905.0 filed Sep. 27, 2005.
H.M. Wallach: “Conditional Random Fields: An Introduction,” CIS Technical Report, Feb. 24, 2004, University of Pennsylvania, USA.
A. Gunawardana et al., “Hidden Conditional Random Fields for Phone Classification,” Eurospeech 2005, Sep. 4, 2005.

Affiliated with

Also associated with

Rating

Hidden conditional random field models for phonetic... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Hidden conditional random field models for phonetic..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hidden conditional random field models for phonetic... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4130948