Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 2838-2841

  Siu, Man Hung ^a   Gish, Herbert ^a   Chan, Arthur ^a   Belfield, William ^a  

^a BBN TECHNOLOGIES   (United States)

Author keywords

Speech recognition; Topic classification; Unsupervised learning

Indexed keywords

SPEECH COMMUNICATION; UNSUPERVISED LEARNING; DATA MINING;

ACOUSTIC MODEL; CONTEXT DEPENDENT; EQUAL ERROR RATE; HIGHLY-CORRELATED; KEYWORD DISCOVERY; SELF-ORGANIZED UNITS; SPEECH RECOGNIZER; TOPIC CLASSIFICATION; ACOUSTIC LATTICES; CONTEXT-DEPENDENT ACOUSTIC MODELING; HMM TRAINING; HMM-BASED; MODEL-BASED OPC; NEW APPROACHES;

SPEECH RECOGNITION;

EID: 79959819374     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. H. Gish, M. Siu, A. Chan and W. Belfield, "Unsupervised training of an HMM-based speech recognition system for topic classification," Interspeech 2009.
2. J. Loof, C. Gollan and H. Ney, "Cross-language bootstrapping for unsupervised acoustic model training: rapid development of a Polish speech recognition system," Interspeech 2009.
3. D. Povey et al, "Subspace Gaussian mixture models for speech recognition," ICASSP 2010.
4. J. Ma and S. Matsoukas, "Unsupervised training on large amount of Arabic broadcast data," ICASSP 2007.
5. Y. Zhang and J. Glass, "Towards multi-speaker unsupervised speech pattern discovery," in ICASSP, 2010
6. J. Cohen, "Segmenting speech using dynamic programming," Journal of Acoustic Society of America, pp. 1430-1437, May 1981.
7. H. Gish and K. Ng, "A segmental speech model with applications to word spotting," in ICASSP, 1993, pp. 447-450.
8. H. Gish and K. Ng, "Parametric trajectory models for speech recognition," in ICSLP, 1996, pp. 466-469.
9. S. Matsoukas et al, "Advances in transcript of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system," IEEE TASLP, vol. 14, pp. 1541-1555, 2006.
10. W. Campbell and F. Richardson, "Discriminative feature selection using support vector machines," in NIPS, 2007.
11. J. Wintrode and S. Kulp, "Confidence-Based Techniques for Rapid and Robust Topic Identification of Conversational Telephone Speech," Interspeech 2009.
12. Chih-Chung Chang and Chih-Jen Lin, LIBSVM: a library for support vector machines, 2001, Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm.
13. T. Hazen, F. Richardson, and A. Margolis, "Topic identification from audio recordings using word and phone recognition lattices," in ASRU, 2007.