Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery

Computer Speech and Language

Volumn 28, Issue 1, 2014, Pages 210-223

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

^a BBN TECHNOLOGIES   (United States)

Author keywords

Keyword discovery; Self learning Speech recognition; Topic identification; Unsupervised training

Indexed keywords

CONTEXT DEPENDENT; HIGHLY-CORRELATED; KEYWORD DISCOVERY; SELF-LEARNING; SWITCHBOARD CORPUS; TOPIC CLASSIFICATION; TOPIC IDENTIFICATION; UNSUPERVISED TRAINING;

ELECTRIC SWITCHBOARDS; OPTIMIZATION; SPEECH RECOGNITION;

TRANSCRIPTION;

EID: 84885423493     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2013.05.002     Document Type: Article

References (27)

1. W. Belfield, and H. Gish A topic classification system based on parametric trajectory mixture models Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 2003 1269 1272
2. L. Burget, P. Matějka, and J. Černocký Discriminative training techniques for acoustic language identification Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 2006
3. W. Campbell, and F. Richardson Discriminative feature selection using support vector machines NIPS 2007
4. C.-C. Chang, and C.-J. Lin LIBSVM: a library for support vector machines 2001 Software available at: http://www.csie.ntu.edu.tw/cjlin/libsvm
5. J. Cohen Segmenting speech using dynamic programming Journal of Acoustic Society of America 1981 1430 1437
6. A. Garcia, and H. Gish Keyword spotting of arbitrary words using minimal speech resources Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 2006
7. H. Gish, and K. Ng A segmental speech model with applications to word spotting Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 1993 447 450
8. H. Gish, and K. Ng Parametric trajectory models for speech recognition Proc. of the Inter. Conf. on Spoken Language Processing (ICSLP) 1996 466 469
9. H. Gish, M. Siu, and W. Belfield Unsupervised training of an HMM-based speech recognition system for topic classification Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2009
10. D. Harwath, T. Hazen, and J.R. Glass Zero resource spoken audio corpus analysis Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 2013
11. T. Hazen, and A. Margolis Discriminative feature weighting using MCE training for topic identification of spoken audio recording Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 2008 4965 4968
12. T. Hazen, F. Richardson, and A. Margolis Topic identification from audio recordings using word and phone recognition lattices Proc. of IEEE Automatic Speech Recognition and Understanding Workshop 2007
13. A. Jansen, K. Church, and H. Hermansky Towards spoken term discovery at scale with zero resources Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2010
14. L. Lamel, J. Gauvain, and G. Adda Lightly supervised and unsupervised acoustic model training Computer Speech and Language 16 2002 115 129
15. M. Levit, A. Gorin, and J. Wright Multipass algorithm for acquisition of salient acoustic morphemes Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2001 1645 1648
16. H. Li, B. Ma, and C. Lee A vector space modeling approach to spoken language identification IEEE Transactions on Audio, Speech and Language Processing 15 1 2007 271 284
17. J. Ma, and R. Schwartz Unsupervised versus supervised training of acoustic models Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2008 2374 2377
18. S. Matsoukas Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system IEEE Transactions on Audio, Speech and Language Processing 14 2006 1541 1555
19. P. Nowell, and R. Moore The application of dynamic programming techniques to non-word based topic spotting Proc. of the European Conference on Speech Comm. and Tech. (EUROSPEECH) 1995 1355 1358
20. A. Park, and J. Glass Towards unsupervised pattern discovery in speech Proc. of IEEE Automatic Speech Recognition and Understanding Workshop 2005 53 58
21. P. Schwartz, P. Matejka, and J. Cernocky Towards lower error rates in phoneme recognition Proc. of TSD 2004
22. M. Siu, H. Gish, A. Chan, and W. Belfield Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2010 2838 2841
23. M. Siu, H. Gish, S. Lowe, and A. Chan Unsupervised audio patterns discovery using hmm-based self-organized units Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2011
24. J. Wintrode, and S. Kulp Confidence-based techniques for rapid and robust topic identification of conversational telephone speech Proc. of the Annual Conference of the International Speech Communication Association (INTERSPEECH) 2009
25. G. Zavaliagkos, M. Siu, T. Colthurst, and J. Billa Using untranscribed training data to improve performance Proc. of the Inter. Conf. on Spoken Language Processing (ICSLP) 1998
26. Y. Zhang, and J. Glass Towards multi-speaker unsupervised speech pattern discovery Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP) 2010
27. M.A. Zissman Automatic language identification using Gaussian mixture and hidden Markov models Proc. of the IEEE Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP), vol. 2 1993 399 402