Cross-lingual subspace Gaussian mixture models for low-resource speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 22, Issue 1, 2014, Pages 17-27

  Lu, Liang ^a   Ghoshal, Arnab ^a   Renals, Steve ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Acoustic modeling; Adaptation; Cross lingual speech recognition; Regularization; Subspace Gaussian mixture model

Indexed keywords

COMMUNICATION CHANNELS (INFORMATION THEORY); HIDDEN MARKOV MODELS; OBJECT RECOGNITION; SPEECH RECOGNITION; AUDIO ACOUSTICS; COMPUTATIONAL LINGUISTICS; GAUSSIAN DISTRIBUTION; MARKOV PROCESSES; TRELLIS CODES;

ACOUSTIC MODEL; ADAPTATION; CROSS-LINGUAL SPEECH RECOGNITION; REGULARIZATION; SUBSPACE GAUSSIAN MIXTURE MODELS;

AUDIO ACOUSTICS; SPEECH RECOGNITION;

EID: 84897937578     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2013.2281575     Document Type: Article

References (40)

1. T. Schultz and A. Waibel, "Fast bootstrapping of LVCSRsystems with multilingual phoneme sets," in Proc. Eurospeech, 1997, pp. 371-374.
2. T. Schultz and A. Waibel, "Multilingual and crosslingual speech recognition," in Proc. DARPAWorkshop Broadcast News Transcript. Understand., 1998.
3. W. Byrne, P. Beyerlein, J. M. Huerta, S. Khudanpur, B. Marthi, J. Morgan, N. Peterek, J. Picone, D. Vergyri, and W. Wang, "Towards language independent acoustic modeling," in Proc. ICASSP, 2000, pp. 1029-1032.
4. V. B. Le and L. Besacier, "First steps in fast acoustic modeling for a new target language: Application to Vietnamese," in Proc. ICASSP, 2005, pp. 821-824.
5. S. Thomas, S. Ganapathy, and H. Hermansky, "Cross-lingual and multi-stream posterior features for low resource LVCSR systems," in Proc. INTERSPEECH, 2010, pp. 877-880.
6. T. Slobada and A. Waibel, "Dictionary learning for spontaneous speech recognition," in Proc. ICSLP, 1996, pp. 2328-2331.
7. R. Singh, B. Raj, and R. M. Stern, "Automatic generation of phone sets and lexical transcriptions," in Proc. ICASSP, 2000, pp. 1691-1694.
8. N. Goel, S. Thomas, M. Agarwal, P. Akyazi, L. Burget, K. Feng, A. Ghoshal, O. Glembek, M. Karafiát, D. Povey, A. Rastrow, R. C. Rose, and P. Schwarz, "Approaches to automatic lexicon learning with limited training examples," in Proc. ICASSP, 2010, pp. 5094-5097.
9. T. Schultz and A. Waibel, "Language-independent and language-adaptive acoustic modeling for speech recognition," Speech Commun., vol. 35, no. 1, pp. 31-52, 2001.
10. T. Schultz, "GlobalPhone: A multilingual speech and text database developed at Karlsruhe University," in Proc. ICLSP, 2002, pp. 345-348.
11. J. Kohler, "Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds," in Proc. ICSLP, 1996, pp. 2195-2198.
12. S. M. 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. Audio, Speech, Lang. Process., vol. 20, no. 3, pp. 875-887, Mar. 2012.
13. K. C. Sim and H. Li, "Robust phone set mapping using decision tree clustering for cross-lingual phone recognition," in Proc. ICASSP, 2008, pp. 4309-4312.
14. K. C. Sim, "Discriminative product-of-expert acoustic mapping for cross-lingual phone recognition," in Proc. ASRU, 2009, pp. 546-551.
15. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. ICASSP, 2000, pp. 1635-1638.
16. A. Stolcke, F. Grézl, M. Y. Hwang, X. Lei, N. Morgan, and D. Vergyri, "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons," in Proc. ICASSP, 2006, pp. 321-324.
17. O. Çetin, M. Magimai-Doss, K. Livescu, A. Kantor, S. King, C. Bartels, and J. Frankel, "Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPs," in Proc. ASRU, 2007, pp. 36-41.
18. Y. Qian, J. Xu, D. Povey, and L. Jia, "Strategies for using MLP based features with limited target-language training data," in Proc. ASRU, 2011, pp. 354-358.
19. C. Plahl, R. Schluter, and H. Ney, "Cross-lingual portability of Chinese and English neural network features for French and German LVCSR," in Proc. ASRU, 2011, pp. 371-376.
20. P. Lal, "Cross-lingual automatic speech recognition using tandem features," Ph.D. thesis, The Univ. of Edinburgh, Edinburgh, U.K., 2011.
21. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pretrained deep neural networks for large-vocabulary speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 20, no. 1, pp. 30-42, Jan. 2012.
22. P. Swietojanski, A. Ghoshal, and S. Renals, "Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR," in Proc. IEEE SLT, 2012, pp. 246-251.
23. G. Aradilla, H. Bourlard, and M. Magimai-Doss, "Using KL-based acoustic models in a large vocabulary recognition task," in Proc. INTERSPEECH, 2008.
24. D. Imseng, R. Rasipuram, and M. Magimai-Doss, "Fast and flexible kullback-leibler divergence based acoustic modelling for non-native speech recognition," in Proc. ASRU, 2011, pp. 348-353.
25. D. Imseng, H. Bourlard, and P. N. Garner, "Using KL-divergence and multilingual informaiton to improve ASR for under-resourced languages," in Proc. ICASSP, 2012, pp. 4869-4872.
26. D. Povey, L. Burget, M. Agarwal, P. Akyazi, F. Kai, A. Ghoshal, O. Glembek, N. Goel, M. Karafiát, A. Rastrow, R. C. Rose, P. Schwarz, and S. Thomas, "The subspace Gaussian mixture model - A structured model for speech recognition," Comput. Speech Lang., vol. 25, no. 2, pp. 404-439, 2011.
27. L. Burget, P. Schwarz, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N. Goel, M. Karafiát, D. Povey, A. Rastrow, R. Rose, and S. Thomas, "Multilingual acousticmodeling for speech recognition based on subspace Gaussian mixture models," in Proc. IEEE ICASSP, 2010, pp. 4334-4337.
28. L. Lu, A. Ghoshal, and S. Renals, "Regularized subspace Gaussian mixture models for cross-lingual speech recognition," in Proc. IEEE ASRU, 2011, pp. 922-932.
29. L. Lu, A. Ghoshal, and S. Renals, "Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition," in Proc. ICASSP, 2012, pp. 4887-4877-4880.
30. L. Lu, A. Ghoshal, and S. Renals, "Regularized subspace Gaussian mixture models for speech recognition," IEEE Signal Process. Lett., vol. 18, no. 7, pp. 419-422, 2011.
31. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction. New York, NY, USA: Springer, 2005.
32. G. Sivaram, S. K. Nemala, M. Elhilali, T. D. Tran, and H. Hermansky, "Sparse coding for speech recognition," in Proc. ICASSP, 2010, pp. 4346-4349.
33. T. N. Sainath, A. Carmi, D. Kanevsky, and B. Ramabhadran, "Bayesian compressive sensing for phonetic classification," in Proc. ICASSP, 2010, pp. 4370-4373.
34. D. L. Donoho, "Compressed sensing," IEEE Trans. Inf. Theory, vol. 52, no. 4, pp. 1289-1306, Apr. 2006.
35. M. A. T. Figueiredo, R. D. Nowak, and S. J. Wright, "Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems," IEEE J. Sel. Topics Signal Process., vol. 1, no. 4, pp. 586-597, Dec. 2007.
36. A. K. Gupta and D. K. Nagar, Matrix Variate Distributions, ser.Monographs and Surveys in Pure and Applied Mathematics. Boca Raton, FL, USA: Chapman & Hall/CRC, 1999, vol. 104.
37. O. Siohan, C. Chesta, and C. H. Lee, "Joint maximum a posteriori adaptation of transformation and HMM parameters," IEEE Trans. Speech Audio Process., vol. 9, no. 4, pp. 417-428, May 2001. (Pubitemid 32372183)
38. P. Dutilleul, "The MLE algorithm for the matrix normal distribution," J. Statist. Comput. Simulat., vol. 64, no. 2, pp. 105-123, 1999.
39. D. Povey, "A tutorial-style introduction to subspace Gaussian mixture models for speech recognition," Microsoft Research, MSR-TR-2009-111, 2009, Tech. Rep.
40. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovský, G. Semmer, and K. Veselý, "The Kaldi speech recognition toolkit," in Proc. ASRU, 2011.