Hierarchical large-margin Gaussian mixture models for phonetic classification

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

Volumn , Issue , 2007, Pages 272-277

  Chang, Hung An ^a   Glass, James R ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Committee classifier; Hierarchical classifier; Large margin GMM; Phonetic classification

Indexed keywords

CLASSIFIERS; GAUSSIAN DISTRIBUTION; LEARNING SYSTEMS; LINGUISTICS; MIXTURES; SET THEORY; SPEECH; SPEECH ANALYSIS; SPEECH RECOGNITION; TRELLIS CODES;

AUTOMATIC SPEECH RECOGNITION (ASR); CONTEXT INDEPENDENT; GAUSSIAN MIXTURE MODEL (GMM); HIERARCHICAL CLASSIFIERS; LOCAL MINIMUMS; LOSS FUNCTIONS; PARAMETER SPACES; PHONETIC CLASSIFICATION; TEST SETS; TWO STAGES;

CLASSIFICATION (OF INFORMATION);

EID: 44849141781     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. A.K. Halberstadt and J.R. Glass, "Heterogeneous acoustic measurements for phonetic classification," Proceedings of Eurospeech, pp. 401-404, 1997.
2. F. Sha and L.K. Saul, "Large margin gaussian mixture modeling for phonetic classification and recognition," Proceedings of ICASSP, pp. 265-268, 2006.
3. A. Gunawardana, M. Mahajan, A. Acero, and J.C. Platt, "Hidden conditional random fields for phone classification," Proceedings of Eurospeech, 2005.
4. R. Rifkin, K. Schutte, M. Saad, J. Bouvire, and J.R. Glass, "Noise robust phonetic classification with linear regularized least squares and second-order features," Proceedings of ICASSP, pp. 881-884, 2007.
5. A.K. Halberstadt and J.R. Glass, "Heterogeneous acoustic measurements and multiple classifiers for speech recognition," Proceedings of ICSLP, 1998.
6. F. Sha and L.K. Saul, "Comparison of large margin training to other discriminative methods for phonetic recoginition by hidden markov models," Proceedings of ICASSP, pp. 313-316, 2007.
7. B.-H. Juang, W. Chou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 5, no. 3, pp. 257-265, 1997.
8. K.F. Lee and H.W. Hon, "Speaker-independent phone recognition using hidden markov models," IEEE Transactions on Acoustic, Speech, and Signal Processing, vol. 37, no. 11, pp. 1641-1648, 1988.
9. J.R. Schewchuk, "An introduction to conjugate gradient method without the agonizing pain," C.M.U., 1994.
10. L.Vandenberghe and S.P.Boyd, "Semidefinite programming," SIAM Review, vol. 38, no. 1, pp. 49-95, March 1996.
11. T. Shinozaki and M. Ostendorf, "Cross-validation EM training for robust parameter estimation," Proceedings of ICASSP, pp. 437-440, 2007.
12. L. Gillick and S.J. Cox, "Some statistical issues in the comparison of speech recognition algorithms," Proceedings of ICASSP, pp. 532-535, 1989.
13. John S. Garofolo et al, "TIMIT acoustic-phonetic continuous speech corpus," Linguistic Data Consortium, 1993.
14. X. Li, H. Jiang, and C. Liu, "Large margin HMMs for speech recognition," Proceedings of ICASSP, pp. 513-516, 2005.
15. D. Yu, L. Deng, X. He, and A. Acero, "Large-margin minimum classification error training for large-scale speech recognition tasks," Proceedings of ICASSP, pp. 1137-1140, 2007.