Submodular data selection with acoustic and phonetic features for automatic speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 2015-August, Issue , 2015, Pages 4629-4633

  Ni, Chongjia ^a   Wang, Lei ^a   Liu, Haibo ^b   Leung, Cheung Chi ^a   Lu, Li ^b   Ma, Bin ^a  

^a INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

^b TENCENT AI LAB   (China)

Author keywords

Active learning; automatic speech recognition; data selection; submodular optimization

Indexed keywords

AUDIO SIGNAL PROCESSING; DATA REDUCTION; FEATURE EXTRACTION; GAUSSIAN DISTRIBUTION; LINGUISTICS; SPEECH; SPEECH COMMUNICATION; TRANSCRIPTION;

ACTIVE LEARNING; AUTOMATIC SPEECH RECOGNITION; CHARACTER ERROR RATES; DATA SELECTION; FEATURE DISTRIBUTION; GAUSSIAN MIXTURE MODEL; GENERALIZED FUNCTIONS; SUBMODULAR OPTIMIZATIONS;

SPEECH RECOGNITION;

EID: 84946012970     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178848     Document Type: Conference Paper

References (31)

1. F. Wessel, and H. Ney, "Unsupervised Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition," IEEE Trans. on Speech and Audio Processing. 2005,13(1):23-31
2. T. Kemp, A. Waibel, "Unsupervised Training of a Speech Recognizer: Recent Experiments," in Proc. Eurospeech 1999, pp. 2725-2728
3. D. Charlet, "Confidence-measure-driven Unsupervised Incremental Adaptation for HMM-based Speech Recognition," in Proc. ICASSP 2001, pp. 357-360
4. G. Tur, D. Hakkani-Tur and R. E. Shapire, "Combining Active and Semi-supervised Learning for Spoken Language Understanding," Speech Communication, 2005,45(2):171-186
5. X. Zhu, "Semi-supervised Learning Literature Survey," Computer Sciences Technical Report 1530, University of Wisconsin-Madison, 2005b
6. D. Yu, B. Varadarajan, L. Deng and A. Acero, "Active Learning and Semi-Supervised Learning for Speech Recognition: A Unified Framework Using the Global Entropy Reduction Maximization Criterion," Computer Speech and Language, 2010, 24(3): 433-444
7. B. Settles, "Active Learning Literature Survey," Computer Sciences Technical Report 1648, University of Wisconsin-Madison, 2010
8. O. Siohan, "Training Data Selection Based on Context-Dependent State Matching," in Proc. ICASSP 2014, pp. 3316-3319
9. N. Itoh, T. N. Sainath, D. N. Jiang, J. Zhou, and B. Ramabhadran, "N-Best Entropy Based Data Selection for Acoustic Modeling," in Proc. ICASSP 2012, pp. 4133-4136
10. Y. Wu, R. Zhang, and A. Rudnicky, "Data Selection for Speech Recognition," in Proc. ASRU 2007, pp. 562-565
11. Y. Hamanaka, K. Shinoda, T. Tsutaoka, S. Furui, T. Emori, and T. Koshinaka, "Committee-Based Active Learning for Speech Recognition," IEICE Trans. on Information and Systems, 2011, 10: 2015-2013
12. D. Hakkani-Tur, G. Riccardi, and A. Gorin, "Active Learning for Automatic Speech Recognition, in Proc. ICASSP 2002, pp. 3904-3907
13. G. Riccardi and D. Hakkani-Tur, "Active and Unsupervised Learning for Automatic Speech Recognition, in Proc. Eurospeech 2003, pp. 1825-1828
14. G. Tur, R. E. Schapire, and D. Hakkani-Tur, "Active Learning for Spoken Language Understanding," in Proc. ICASSP 2003, pp. I-276-I-279
15. T. M. Kamm and G. G. L. Meyer, "Selective Sampling of Training Data for Speech Recognition," in Proc. Human Language Technology Conf., San Diego, CA, 2002
16. K. Wei, Y. Liu, K. Kirchhoff, C. Bartels and J. Bilmes, "Submodular Subset Selection for Large-Scale Speech Training Data," in Proc. ICASSP 2014, pp. 3311-3315
17. K. Wei, Y. Liu, K. Kirchhoff, and J. Bilmes, "Using Document Summarization Techniques for Speech Data Subset Selection," in Proc. NAACL/HLT-2013, pp. 721-726
18. Y. Shinohara, "A Submodular Optimization Approach to Sentence Set Selection," in Proc. ICASSP 2014, pp. 4140-4143
19. H. Lin and J. Bilmes, "How to Select a Good Training-data Subset for Transcription: Submodular Active Selection for Sequences," in Proc. Interspeech 2009, pp. 2859-2862
20. K. Wei, Y. Liu, K. Kirchhoff, and J. Bilmes, "Unsupervised Submodular Subset Selection for Speech Data," in Proc. ICASSP 2014, pp. 4107-4111
21. G. Nemhauser, L. Wolsey, and M. Fisher, "An Analysis of Approximations for Maximizing Submodular Set Function-I," Mathematical Programming,1978, 14(1):265-294
22. U. Feige, "A Threshold of ln n for Approximating Set Cover," Journal of the ACM (JACM), 1998,45(4):634-652
23. F. Bach, "Learning with Submodular Functions: A Convex Optimization Perspective," Foundations and Trends ® in Machine Learning," 2013,6(2-3): 145-373
24. T. Kinnunen, and H. Li, "An Overview of Text-independent Speaker Recognition: From Features to Supervectors," Speech Communication, 2010:52(1):12-40
25. Y. Zhang, "Unsupervised Speech Processing with Applications to Query-by-Example Spoken Term Detection," Ph.D Thesis
26. H. Wang, T. Lee, C.-C. Leung, B. Ma and H. Li, "Unsupervised Mining of Acoustic Subword Units With Segment-level Gaussian Posteriorgrams," in Proc. Interspeech 2013, pp.2297-2301
27. H. Wang, T. Lee, C.-C. Leung, B. Ma and H. Li, "Acoustic Segment Modeling with Spectral Clustering Methods," IEEE Trans. On Audio, Speech and Language Processing, 2015,23(2):264-277
28. L. Zhang, C.-C. Leung, L. Xie, B. Ma, and H. Li, "Acoustic TextTiling for Story Segmentation of Spoken Documents," in Proc. ICASSP 2012, pp.5121-5124
29. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for Model and Feature Space Discriminative Training," in Proc. ICASSP 2008, pp. 4057-4060
30. C. Ni, C.-C. Leung, L. Wang, N. F. Chen and B. Ma, "Unsupervised Data Selection and Word Morph Mixed Language Model for Tamil Low Resource Spoken Keyword Spotting," in Proc. ICASSP 2015
31. N. F. Chen, C. Ni, I-Fan Chen, S. Sivadas, V. T. Pham, H. Xu, X. Xiao, T. S. Lau, S. Leow, B. P. Lim, C.-C. Leung, L. Wang, C.-H. Lee, A. Goh, E. S. Chng, B. Ma, H. Li, "Lowresource Keyword Search Strategies for Tamil," in Proc. ICASSP 2015