Unsupervised mining of acoustic subword units with segment-level gaussian posteriorgrams

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2013, Pages 2297-2301

  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

Gaussian by segment matrix; Non negative matrix factorization; Normalized cut; Segment level posteriorgrams; Unsupervised acoustic unit mining

Indexed keywords

CLUSTERING ALGORITHMS; GAUSSIAN DISTRIBUTION; IMAGE SEGMENTATION;

CLUSTERING RESULTS; GAUSSIAN MIXTURE MODEL; LABELING METHODS; MATRIX FACTORIZATIONS; NONNEGATIVE MATRIX FACTORIZATION; NORMALIZED CUTS; SEGMENT- LEVEL POSTERIORGRAMS; UNSUPERVISED SEGMENTATION;

MATRIX ALGEBRA;

EID: 84906281211     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (29)

1. R. Singh, B. Raj, and R. Stern, "Automatic generation of subword units for speech recognition systems, " IEEE Trans. SAP, vol. 10, no. 2, pp. 89-99, 2002.
2. M.-H. Siu, H. Gish, A. Chan, and W. Belfield, "Im- proved topic classification and keyword discovery using an HMM-based speech recognizer trained without super- vision, " in Proc. INTERSPEECH, 2010, pp. 2838-2841.
3. 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.
4. C.-H. Lee, F. Soong, and B.-H. Juang, "A segment model based approach to speech recognition, " in Proc. ICASSP, 1988, pp. 501-541.
5. M. Bacchiani and M. Ostendorf, "Joint lexicon, acous- Tic unit inventory and model design, " Speech Communication, vol. 29, no. 2, pp. 99-114, 1999.
6. J. Shi and J. Malik, "Normalized cuts and image segmentation, " IEEE Trans. PAMI, vol. 22, no. 8, pp. 888-905, 2000.
7. D. Seung and L. Lee, "Algorithms for non-negative matrix factorization, " Advances in neural information processing systems, vol. 13, pp. 556-562, 2001.
8. Y. Zhang and J. Glass, "Unsupervised spoken keyword spotting via segmental DTW on Gaussian posterior- grams, " in Proc. ASRU, 2009, pp. 398-403.
9. B. Ma, D. Zhu, and H. Li, "Acoustic segment modeling for speaker recognition, " in Proc. ICME, 2009, pp. 1668- 1671.
10. J. Reed and C.-H. Lee, "A study on music genre classifica- Tion based on universal acoustic models, " in Proc. ISMIR, 2006, pp. 89-94.
11. H. Gish and K. Ng, "A segmental speech model with applications to word spotting, " in Proc. ICASSP, vol. 2, 1993, pp. 447-450.
12. 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.
13. T. Hazen, M.-H. Siu, H. Gish, S. Lowe, and A. Chan, "Topic modeling for spoken documents using only pho- netic information, " in Proc. ASRU, 2011, pp. 395-400.
14. B. Varadarajan and S. Khudanpur, "Automatically learn- ing speaker-independent acoustic subword units, " in Proc. INTERSPEECH, 2008, pp. 1333-1336.
15. H. Singer and M. Ostendorf, "Maximum likelihood suc- cessive state splitting, " in Proc. ICASSP, vol. 2, 1996, pp. 601-604.
16. C. Lee and J. Glass, "A nonparametric bayesian approach to acoustic model discovery, " in Proc. ACL, 2012.
17. A. Jansen and K. Church, "Towards unsupervised training of speaker independent acoustic models, " in Proc. INTER- SPEECH, 2011, pp. 1693-1696.
18. A. Jansen, S. Thomas, and H. Hermansky, "Weak top- down constraints for unsupervised acoustic model training, " in Proc. ICASSP, 2013.
19. G. Aradilla, J. Vepa, and H. Bourlard, "Using posterior- based features in template matching for speech recognition, " in Proc. INTERSPEECH, 2006, pp. 1186-1189.
20. T. Hazen, W. Shen, and C. White, "Query-by-example spoken term detection using phonetic posteriorgram templates, " in Proc. ASRU, 2009, pp. 421-426.
21. S. Deerwester, S. Dumais, G. Furnas, T. Landauer, and R. Harshman, "Indexing by latent semantic analysis, " Journal of the American society for information science, vol. 41, no. 6, pp. 391-407, 1990.
22. A. Ng, M. Jordan, Y.Weiss et al., "On spectral clustering: Analysis and an algorithm, " Advances in neural information processing systems, vol. 2, pp. 849-856, 2002.
23. W. Xu, X. Liu, and Y. Gong, "Document clustering based on non-negative matrix factorization, " in Proc. 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, 2003, pp. 267- 273.
24. C. Ding, T. Li, W. Peng, and H. Park, "Orthogonal non- negative matrix T-factorizations for clustering, " in Proc. 12th ACM SIGKDD international conference on Knowledge discovery and data mining, 2006, pp. 126-135.
25. C. Ding, T. Li, and W. Peng, "On the equivalence be- Tween non-negative matrix factorization and probabilistic latent semantic indexing, " Computational Statistics and Data Analysis, vol. 52, no. 8, pp. 3913-3927, 2008.
26. Y. Muthusamy, R. Cole, and B. Oshika, The OGI multi- language telephone speech corpus, 1994.
27. S. Siniscalchi, D.-C. Lyu, T. Svendsen, and C.-H. Lee, "Experiments on cross-language attribute detection and phone recognition with minimal target-specific training data, " IEEE Trans. ASLP, vol. 20, no. 3, pp. 875-887, 2012.
28. C. Manning, P. Raghavan, and H. Schütze, Introduction to information retrieval. Cambridge University Press Cambridge, 2008.
29. T. Sainath, D. Kanevsky, and B. Ramabhadran, "Broad phonetic class recognition in a hidden Markov model framework using extended Baum-Welch transformations, " in Proc. ASRU, 2007, pp. 306-311.