Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR

2012 IEEE Workshop on Spoken Language Technology, SLT 2012 - Proceedings

Volumn , Issue , 2012, Pages 246-251

  Swietojanski, Pawel ^a   Ghoshal, Arnab ^a   Renals, Steve ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Cross lingual ASR; Deep Neural Networks; GlobalPhone; RBM pretraining

Indexed keywords

ACOUSTIC DATA; ACOUSTIC MODEL; CROSS-LINGUAL; DEEP NEURAL NETWORKS; EMISSION DENSITY; GAUSSIAN MIXTURE MODEL (GMMS); GLOBALPHONE; HIDDEN MARKOV MODEL(HMM); HYBRID CONFIGURATIONS; KNOWLEDGE TRANSFER; PRE-TRAINING; RESTRICTED BOLTZMANN MACHINE; SWEDISHS; TANDEM CONFIGURATION; TRAINING DATA;

HIDDEN MARKOV MODELS; KNOWLEDGE MANAGEMENT;

NEURAL NETWORKS;

EID: 84874278045     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SLT.2012.6424230     Document Type: Conference Paper

References (28)

1. T Schultz and AWaibel, "Language independent and language adaptive acoustic modeling for speech recognition," Speech Communication, vol. 35, pp. 31-51, 2001.
2. T Schultz and A Waibel, "Experiments on cross-language acoustic modeling," in Proc. Eurospeech, 2001.
3. F Gŕezl, M Karafíat, and M Janda, "Study of probabilistic and bottle-neck features in multilingual environment," in Proc. IEEE ASRU, 2011.
4. S Thomas, S Ganapathy, and H Hermansky, "Multilingual MLP features for low-resource LVCSR systems," in Proc. IEEE ICASSP, 2012.
5. D Imseng, H Bourlard, and PN Garner, "Using KL-divergence and multilingual information to improve ASR for underresourced languages," in Proc. IEEE ICASSP, 2012.
6. L Burget, P Schwarz, M Agarwal, P Akyaz, K Feng, A Ghoshal, O Glembek, N Goel, M Karafíat, D Povey, A Rastrow, RC Rose, and S Thomas, "Multilingual acoustic modeling for speech recognition based on subspace Gaussian mixture models," in Proc. IEEE ICASSP, 2010.
7. L Lu, A Ghoshal, and S Renals, "Regularized subspace Gaussian mixture models for cross-lingual speech recognition," in Proc. IEEE ASRU, 2011.
8. NT Vu, F Kraus, and T Schultz, "Cross-language bootstrapping based on completely unsupervised training using multilingual A-stabil," in Proc. IEEE ICASSP, 2011.
9. G Hinton, S Osindero, and Y Teh, "A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, pp. 1527-1554, 2006.
10. H Hermansky, DPW Ellis, and S Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. IEEE ICASSP, 2000.
11. F Grézl, M Karafiát, S Kontár, and J C? ernocký, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. IEEE ICASSP, 2007.
12. H Bourlard and N Morgan, Connectionist Speech Recognition-A Hybrid Approach, Kluwer Academic, 1994.
13. S Renals, N Morgan, H Bourlard, M Cohen, and H Franco, "Connectionist probability estimators in HMM speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 2, no. 1, pp. 161-174, 1994.
14. AJ Robinson, "An application of recurrent nets to phone probability estimation," IEEE Transactions on Neural Networks, vol. 5, no. 2, pp. 298-305, 1994.
15. A Mohamed, GE Dahl, and G Hinton, "Acoustic modeling using deep belief networks," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, 2012.
16. GE Dahl, D Yu, L Deng, and A Acero, "Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition," IEEE Transactions on Audio, Speech & Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
17. A Stolcke, F Gŕezl, 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. IEEE ICASSP, 2006.
18. S Thomas and H Hermansky, "Cross-lingual and multistream posterior features for low resource LVCSR systems," in Proc. Interspeech, 2010.
19. O Ç etin, 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 IEEE ASRU, 2007.
20. Y Bengio, P Lamblin, D Popovici, and H Larochelle, "Greedy layer-wise training of deep networks," in Advances in Neural Information Processing Systems 19 (NIPS'06), pp. 153-160. MIT Press, 2007.
21. F Seide, G Li, X Chen, and D Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in Proc. IEEE ASRU, 2011.
22. T Schultz, "GlobalPhone: a multilingual speech and text database developed at Karlsruhe University," in Proc. ICLSP, 2002.
23. P Lal, Cross-Lingual Automatic Speech Recognition using Tandem Features, Ph.D. thesis, The University of Edinburgh, 2011.
24. D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, M Hannemann, P Motĺcek, Y Qian, P Schwarz, J Silovsḱy, G Stemmer, and K Veseĺy, "The Kaldi speech recognition toolkit," in Proc. IEEE ASRU, December 2011.
25. R Gopinath, "Maximum likelihood modeling with Gaussian distributions for classification," in Proc. IEEE ICASSP, May 1998, vol. 2, pp. 661-664.
26. D Povey, D Kanevsky, B Kingsbury, B Ramabhadran, G Saon, and K Visweswariah, "Boosted MMI for model and featurespace discriminative training," in Proc. IEEE ICASSP, 2008, pp. 4057-4060.
27. J Bergstra, O Breuleux, F Bastien, P Lamblin, R Pascanu, G Desjardins, J Turian, D Warde-Farley, and Y Bengio, "Theano: a CPU and GPU math expression compiler," in Proc. SciPy, 2010.
28. D Erhan, Y Bengio, A Courville, P-A Manzagol, P Vincent, and S Bengio, "Why does unsupervised pre-training help deep learning?," Journal of Machine Learning Research, vol. 11, pp. 625-660, February 2010.