Regularized subspace Gaussian mixture models for cross-lingual speech recognition

2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings

Volumn , Issue , 2011, Pages 365-370

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

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

^b SAARLAND UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODELLING; CROSS-LINGUAL; GAUSSIAN MIXTURE MODEL; MULTIPLE SOURCE; NUMERICAL INSTABILITY; SINGLE SOURCE; SOURCE LANGUAGE; STATE VECTOR; TARGET LANGUAGE; WORD ERROR RATE;

COMMUNICATION CHANNELS (INFORMATION THEORY); NATURAL LANGUAGE PROCESSING SYSTEMS; OBJECT RECOGNITION; TRANSCRIPTION; VECTORS;

SPEECH RECOGNITION;

EID: 84858952433     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2011.6163959     Document Type: Conference Paper

References (19)

1. T. Schultz and A. Waibel, "Fast bootstrapping of LVCSR systems with multilingual phoneme sets," in Proc. Eurospeech. Citeseer, 1997, pp. 371-374.
2. -, "Multilingual and crosslingual speech recognition," in Proc. DARPA Workshop on Broadcast News Transcription and Understanding. Citeseer, 1998.
3. -, "Language-independent and language-adaptive acoustic modeling for speech recognition," Speech Communication, vol. 35, No. 1, pp. 31-52, 2001.
4. T. Schultz, "GlobalPhone: a multilingual speech and text database developed at Karlsruhe University," in Proc. ICLSP, 2002, pp. 345-348.
5. N. Vu, F. Kraus, and T. Schultz, "Multilingual A-stabil: A new confidence score for multilingual unsupervised training," in IEEE Workshop on Spoken Language Technology, SLT, 2010.
6. -, "Cross-language bootstrapping based on completely unsupervised training using multilingual A-stabil," in Proc. ICASSP. IEEE, 2011, pp. 5000-5003.
7. P. Beyerlein, W. Byrne, J. Huerta, S. Khudanpur, B. Marthi, J. Morgan, N. Peterek, J. Picone, and W. Wang, "Towards language independent acoustic modeling," in Proc. ICASSP. IEEE, 2000, pp. 1029-1032.
8. V. Le and L. Besacier, "First steps in fast acoustic modeling for a new target language: application to Vietnamese," in Proc. ICASSP. IEEE, 2005, pp. 821-824.
9. K. Sim and H. Li, "Robust phone set mapping using decision tree clustering for cross-lingual phone recognition," in Proc. ICASSP. IEEE, 2008, pp. 4309-4312.
10. K. Sim, "Discriminative product-of-expert acoustic mapping for cross-lingual phone recognition," in Proc. ASRU. IEEE, 2009, pp. 546-551.
11. H. Hermansky, D. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. ICASSP. IEEE, 2000, pp. 1635-1638.
12. A. Stolcke, F. Grézl, M. Hwang, X. Lei, N. Morgan, and D. Vergyri, "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons," in Proc. ICASSP. IEEE, 2006, pp. 321-324.
13. 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. IEEE, 2007, pp. 36-41.
14. 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.
15. P. Lal, "Cross-lingual Automatic Speech Recognition using Tandem Features," Ph.D. dissertation, The University of Edinburgh, 2011.
16. D. Povey, L. Burget, M. Agarwal, P. Akyazi, F. Kai, A. Ghoshal, O. Glembek, N. Goel, M. Karafiát, A. Rastrow, R. Rose, P. Schwarz, and S. Thomas, "The subspace Gaussian mixture model-A structured model for speech recognition," Computer Speech & Language, vol. 25, No. 2, pp. 404-439, 2011.
17. 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 acoustic modeling for speech recognition based on subspace Gaussian mixture models," in Proc. ICASSP. IEEE, 2010, pp. 4334-4337.
18. L. Lu, A. Ghoshal, and S. Renals, "Regularized subspace Gaussian mixture models for speech recognition," IEEE Signal Processing Letters, vol. 18, No. 7, pp. 419-422, 2011.
19. D. Povey, "A tutorial-style introduction to subspace Gaussian mixture models for speech recognition," MSR-TR-2009-111, Microsoft Research, Tech. Rep., 2009.