Acoustic segment modeling with spectral clustering methods

IEEE/ACM Transactions on Audio Speech and Language Processing

Volumn 23, Issue 2, 2015, Pages 264-277

  Wang, Haipeng ^a   Lee, Tan ^a   Leung, Cheung Chi ^b   Ma, Bin ^b   Li, Haizhou ^b  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

^b INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

Author keywords

Acoustic segment modeling; multiview segment clustering; sub word unit discovery; unsupervised training; zero resource query by example spoken term detection

Indexed keywords

ITERATIVE METHODS; MATRIX ALGEBRA; SPEECH ANALYSIS; STATISTICAL TESTS;

ACOUSTIC SEGMENT MODELS; MULTI-VIEWS; SPOKEN TERM DETECTIONS; SUB-WORD UNITS; UNSUPERVISED TRAINING;

CLUSTERING ALGORITHMS;

EID: 84921635765     PISSN: 23299290     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASLP.2014.2387382     Document Type: Article

References (66)

1. L. Lamel, J. Gauvain, and G. Adda, "Lightly supervised and unsupervised acoustic model training," Comput. Speech Lang., vol. 16, no. 1, pp. 115-129, 2002.
2. F. Wessel and H. Ney, "Unsupervised training of acoustic models for large vocabulary continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 13, no. 1, pp. 23-31, Jan. 2005.
3. S. Novotney, R. Schwartz, and J. Ma, "Unsupervised acoustic and language model training with small amounts of labelled data," in Proc. ICASSP, 2009, pp. 4297-4300.
4. J. Glass, "Towards unsupervised speech processing," in Proc. ISSPA, 2012, pp. 1-4.
5. C. Lee and J. Glass, "A nonparametric Bayesian approach to acoustic model discovery," in Proc. ACL, 2012, pp. 40-49.
6. A. Jansen, S. Thomas, and H. Hermansky, "Weak top-down constraints for unsupervised acoustic model training," in Proc. ICASSP, 2013, pp. 8091-8095.
7. M. Siu, A. Chan, H. Gish, W. Belfield, and S. Lowe, "Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery," Comput. Speech Lang., vol. 28, no. 1, pp. 210-223, 2014.
8. A. Jansen, E. Dupoux, S. Goldwater, M. Johnson, S. Khudanpur, K. Church, N. Feldman, H. Hermansky, F. Metze, and R. Rose et al., "A summary of the 2012JHU CLSP workshop on zero resource speech technologies and models of early language acquisition," in Proc. ICASSP, 2013, pp. 8111-8115.
9. C. Lee, F. Soong, and B. Juang, "A segment model based approach to speech recognition," in Proc. ICASSP, 1988, pp. 501-541.
10. J. Reed and C. Lee, "A study on music genre classification based on universal acoustic models," in Proc. ISMIR, 2006, pp. 89-94.
11. H. Li, B. Ma, and C. Lee, "A vector space modeling approach to spoken language identification," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 1, pp. 271-284, Jan. 2007.
12. S. Dusan and L. Rabiner, "On the relation between maximum spectral transition positions and phone boundaries," in Proc. Interspeech, 2006, pp. 645-648.
13. Y. Qiao, N. Shimomura, and N. Minematsu, "Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons," in Proc. ICASSP, 2008, pp. 3989-3992.
14. O. Scharenborg, V. Wan, and M. Ernestus, "Unsupervised speech segmentation: An analysis of the hypothesized phone boundaries," J. Acoust. Soc. Amer., vol. 127, no. 2, pp. 1084-1095, 2010.
15. Y. Estevan, V. Wan, and O. Scharenborg, "Finding maximum margin segments in speech," in Proc. ICASSP, 2007, pp. 937-940.
16. A. Torbati, J. Picone, and M. Sobel, "Speech acoustic unit segmentation using hierarchical Dirichlet processes," in Proc. Interspeech, 2013, pp. 637-641.
17. M. Siu, H. Gish, S. Lowe, and A. Chan, "Unsupervised audio patterns discovery using HMM-based self-organized units," in Proc. Interspeech, 2011, pp. 2333-2336.
18. F. Metze, X. Anguera, E. Barnard, M. Davel, and G. Gravier, "Language independent search in MediaEval's spoken web search task," Comput. Speech Lang., vol. 28, no. 5, pp. 1066-1082, 2014.
19. A. Garcia and H. Gish, "Keyword spotting of arbitrary words using minimal speech resources," in Proc. ICASSP, 2006, pp. 949-952.
20. M. Siu, H. Gish, A. Chan, and W. Belfield, "Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision," in Proc. Interspeech, 2010, pp. 2838-2841.
21. M. Bacchiani and M. Ostendorf, "Joint lexicon, acoustic unit inventory and model design," Speech Commun., vol. 29, no. 2, pp. 99-114, 1999.
22. H. Gish and K. Ng, "A segmental speech model with applications to word spotting," in Proc. ICASSP, 1993, vol. 2, pp. 447-450.
23. H. Wang, C.-C. Leung, T. Lee, B. Ma, and H. Li, "An acoustic segment modeling approach to query-by-example spoken term detection," in Proc. ICASSP, 2012, pp. 5157-5160.
24. H. Singer and M. Ostendorf, "Maximum likelihood successive state splitting," in Proc. ICASSP, 1996, pp. 601-604.
25. B. Varadarajan and S. Khudanpur, "Automatically learning speakerindependent acoustic subword units," in Proc. Interspeech, 2008, pp. 1333-1336.
26. C. Chung, C. Chan, and L. Lee, "Unsupervised discovery of linguistic structure including two-level acoustic patterns using three cascaded stages of iterative optimization," in Proc. ICASSP, 2013, pp. 8081-8085.
27. A. Jansen and K. Church, "Towards unsupervised training of speaker independent acoustic models," in Proc. Interspeech, 2011, pp. 1693-1692.
28. R. Singh, B. Raj, and R. Stern, "Automatic generation of subword units for speech recognition systems," IEEE Trans. Speech Audio Process., vol. 10, no. 2, pp. 89-99, Feb. 2002.
29. C. Lee, Y. Zhang, and J. Glass, "Joint learning of phonetic units and word pronunciations for ASR," in Proc. EMNLP, 2013, pp. 182-192.
30. B. Ma, D. Zhu, and H. Li, "Acoustic segment modeling for speaker recognition," in Proc. ICME, 2009, pp. 1668-1671.
31. M. Siu, O. Lang, H. Gish, S. Lowe, A. Chan, and O. Kimball, "Mllr transforms of self-organized units as features in speaker recognition," in Proc. ICASSP, 2012, pp. 4385-4388.
32. H. Lee, Y. Li, C. Chung, and L. Lee, "Enhancing query expansion for semantic retrieval of spoken content with automatically discovered acoustic patterns," in Proc. ICASSP, 2013, pp. 8297-8301.
33. Y. Zhang and J. Glass, "Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams," in Proc. ASRU, 2009, pp. 398-403.
34. M. Huijbregts, M. McLaren, and D. Leeuwen, "Unsupervised acoustic sub-word unit detection for query-by-example spoken term detection," in Proc. ICASSP, 2011, pp. 4436-4439.
35. C. Chan and L. Lee, "Model-based unsupervised spoken term detection with spoken queries," IEEE Trans. Audio, Speech, Lang. Process., vol. 21, no. 7, pp. 1330-1342, Jul. 2013.
36. J. Garofolo, L. Lamel, W. Fisher, J. Fiscus, and D. Pallett, DARPA TIMIT acoustic-phonetic continuous speech corpus NASA STI/Recon Tech. Rep. N, , 1993.
37. Q. Zhu, A. Stolcke, B. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system," in Proc. Interspeech, 2005, pp. 2141-2144.
38. T. Hazen, W. Shen, and C. White, "Query-by-example spoken term detection using phonetic posteriorgram templates," in Proc. ASRU, 2009, pp. 421-426.
39. L. Zheng, 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.
40. H. Wang, C.-C. Leung, T. Lee, B. Ma, and H. Li, "Shifted-delta MLP features for spoken language recognition," IEEE Signal Process. Lett., vol. 20, no. 1, pp. 15-18, 2013.
41. G. Aradilla, J. Vepa, and H. Bourlard, "Using posterior-based features in template matching for speech recognition," in Proc. Interspeech, 2006, pp. 949-952.
42. F. Grezl, M. Karafiát, and M. Janda, "Study of probabilistic and bottleneck features in multilingual environment," in Proc. ASRU, 2011, pp. 359-364.
43. S. Deerwester, S. Dumais, and T. Landauer et al., "Indexing by latent semantic analysis," JASIS, vol. 41, no. 6, pp. 391-407, 1990.
44. Y. Muthusamy, R. Cole, and B. Oshika, The OGI multi-language telephone speech corpus 1994.
45. L. Van der Maaten and G. Hinton, "Visualizing data using t-SNE," J. Mach. Learn. Res., vol. 9, no. 11, pp. 2579-2605, 2008.
46. A. Ng, M. Jordan, and Y. Weiss, "On spectral clustering: Analysis and an algorithm," in Proc. NIPS, 2001, pp. 849-856.
47. U. Luxburg, "A tutorial on spectral clustering," Statist. Comput., vol. 17, no. 4, pp. 395-416, 2007.
48. M. Tipping and C. Nh, "Sparse kernel principal component analysis," in Proc. NIPS, 2000, pp. 633-639.
49. T. Xia, D. Tao, T. Mei, and Y. Zhang, "Multiview spectral embedding," IEEE Trans. Systems, Man, Cybern. B: Cybern., vol. 40, no. 6, pp. 1438-1446, Jun. 2010.
50. M. Wang, X.-S. Hua, X. Yuan, Y. Song, and L.-R. Dai, "Optimizing multi-graph learning: Towards a unified video annotation scheme," in Proc. ACM Multimedia, 2007, pp. 862-871.
51. S. Boyd and L. Vandenberghe, Convex Optimization. Cambridge, U.K.: Cambridge Univ. Press, 2004.
52. C. Manning, P. Raghavan, and H. Schütze, Introduction to information retrieval 2008.
53. S. Wegmann, D. McAllaster, J. Orloff, and B. Peskin, "Speaker normalization on conversational telephone speech," in Proc. ICASSP, 1996, pp. 339-341.
54. P. Schwarz, "Phoneme recognition based on long temporal context," Ph.D. dissertation, Brno Univ. of Technol., Brno, Czech Republic, 2009.
55. S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, and D. Povey et al., The HTK book. Cambridge, U.K.: Cambridge Univ., 2006.
56. F. Metze, X. Anguera, E. Barnard, and M. Davel et al., "The spoken web search task at MediaEval 2012," in Proc. ICASSP, 2013, pp. 8121-8125.
57. F. Metze, E. Barnard, M. Davel, V. H. , X. Anguera, G. Gravier, and N. Rajput et al., "The spoken web search task," in Proc. MediaEval '12 Workshop, 2012.
58. H. Wang, T. Lee, C.-C. Leung, B. Ma, and H. Li, "Using parallel tokenizers with DTW matrix combination for low-resource spoken term detection," in Proc. ICASSP, 2013, pp. 8545-8549.
59. I. Szöke, L. Burget, and F. Grézl et al., "BUT SWS 2013-massive parallel approach," in Proc. MediaEval '13 Workshop, 2013.
60. A. Abad, R. Fuentes, M. Penagarikano, A. Varona, M. Diez, and G. Bordel, "On the calibration and fusion of heterogeneous spoken term detection systems," in Proc. Interspeech, 2013.
61. A. Azran and Z. Ghahramani, "Spectral methods for automatic multiscale data clustering," in Proc. CVPR, 2006, pp. 190-197.
62. 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.
63. H. Wang, T. Lee, C.-C. Leung, B. Ma, and H. Li, "A graph-based Gaussian component clustering approach to unsupervised acoustic modeling," in Proc. Interspeech, 2014, pp. 875-879.
64. A. Kumar, P. Rai, and H. Daumé, "Co-regularized multi-view spectral clustering," in Proc. NIPS, 2011, pp. 1413-1421.
65. A. Kumar and H. Daumé, "A co-training approach for multi-view spectral clustering," in Proc. ICML, 2011, pp. 393-400.
66. J. Liu, C. Wang, J. Gao, and J. Han, "Multi-view clustering via joint nonnegative matrix factorization," in Proc. SDM, 2013, pp. 252-260.