Revisiting hybrid and GMM-HMM system combination techniques

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2013, Pages 6744-6748

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

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

deep neural networks; hybrid; system combination; tandem; TED

Indexed keywords

DEEP NEURAL NETWORKS; HYBRID; SYSTEM COMBINATION; TANDEM; TED;

HIDDEN MARKOV MODELS; NEURAL NETWORKS;

SIGNAL PROCESSING;

EID: 84890492591     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638967     Document Type: Conference Paper

References (37)

1. JG Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Proc. IEEE ASRU, 1997, pp. 347-352
2. A Stolcke, Y Konig, and M Weintraub, "Explicit word error minimization in n-best list rescoring.," in EUROSPEECH, 1997
3. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus in speech recognition: word error minimization and other appli-cations of confusion networks," Computer Speech and Language, vol. 14, no. 4, pp. 373-400, 2000
4. G Evermann and PC Woodland, "Posterior probability decoding, confidence estimation and system combination," in Proc. NIST Speech Transcription Workshop, 2000
5. C Breslin and MJF Gales, "Generating complementary systems for speech recognition.," in INTERSPEECH, 2006
6. C. Breslin and M. J. F. Gales, "Directed decision trees for generating complementary systems," Speech Communication, vol. 51, no. 3, pp. 284-295, 2009
7. J. Fritsch, M. Finke, and A. Waibel, "Adaptively growing hierarchical mixtures of experts," in Advances in Neural Information Processing Systems, 1997, pp. 459-465
8. MJF Gales and SS Airey, "Product of gaussians for speech recognition," Computer Speech and Language, vol. 20, 2006
9. F. Grezl, M Karafiat, S. Kontar, and J. Cernokcy, "Probabilistic and bottleneck features for LVCSR of meetings," in Proc. IEEE ICASSP, 2007
10. H Hermansky, DPW Ellis, and S Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. IEEE ICASSP, 2000
11. P. Bell, M. Gales, P. Lanchantin, X. Liu, Y. Long, S. Renals, P. Swietojanski, and P. Woodland, "Transcription of multigenre media archives using out-of-domain data," in Proc. IEEE Workshop on Spoken Language Technology, Miami, 2012
12. H. Bourlard and N. Morgan, Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers, 1994
13. 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
14. MJF Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, no. 2, pp. 75-98, April 1998
15. M Federico, M. Cettolo, L. Bentivogli, M. Paul, and S. Stuker, "Overview of the IWSLT 2012 evaluation campaign," in Proc. of the International Workshop on Spoken Language Translation, Hong Kong, HK, December 2012
16. C. Dugast, L. Devillers, and X. Aubert, "Combining TDNN and HMM in a hybrid system for improved continuous-speech recognition," Speech and Audio Processing, IEEE Transactions on, vol. 2, no. 1, pp. 217-223, jan 1994
17. 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
18. M. Hochberg, S. Renals, T. Robinson, and D. Kershaw, "Large vocabulary continuous speech recognition using a hybrid connectionist/ HMM system," in Proc. ICSLP, Yokohama
19. G. Zavaliagkos, Y. Zhao, R. Schwartz, and J. Makhoul, "A hybrid segmental neural net/hidden Markov model system for continuous speech recognition," Speech and Audio Processing, IEEE Transactions on, vol. 2, no. 1, pp. 151-160, jan 1994
20. Y. J. Chung and C. K. Un, "Multilayer perceptrons for statedependent weightings of HMM likelihoods," Speech Communication, vol. 18, no. 1, pp. 79-89, 1996
21. T. N. Sainath, B. Kingsbury, and B. Rambahadron, "Autoencoder bottleneck features using deep belief networks," in Proc. IEEE ICASSP, 2012
22. N Jaitly, P Nguyen, A Senior, and V Vanhoucke, "Application of pretrained deep neural networks to large vocabulary speech recognition," in Interspeech, 2012
23. G Zweig and P Nguyen, "Scarf: A segmental conditional random field toolkit for speech recognition," in Interspeech, 2010, pp. 2858-2861
24. A Morris, A Hagen, H Glotin, and H Bourlard, "Multi-stream adaptive evidence combination for noise robust ASR," Speech Communication, vol. 34, no. 1-2, pp. 25-40, 2001
25. H Xu, D Povey, L Mangu, and J Zhu, "Minimum bayes risk decoding and system combination based on a recursion for edit distance," Computer Speech and Language, vol. 25, no. 4, pp. 802-828, October 2011
26. M. Cettolo, C. Girardi, and M. Federico, "Wit3: Web inventory of transcribed and translated talks," in Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT), Trento, Italy, May 2012, pp. 261-268
27. E. Hasler, P. Bell, A. Ghoshal, B. Haddow, P. Koehn, F. McInnes, S. Renals, and P. Swietojanski, "The UEDIN systems for the IWSLT 2012 evaluation," in Proc. IWSLT, 2012
28. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motl?cek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, and K. Vesely, "The Kaldi speech recognition toolkit," in Proc. IEEE ASRU, December 2011
29. 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
30. 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
31. T. Hain, L. Burget, J. Dines, P.N. Garner, F. Grezl, A.E. Hannani, M. Huijbregts, M. Karafiat, M. Lincoln, and V. Wan, "Transcribing meetings with the AMIDA systems," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 2, pp. 486-498, 2012
32. Y. Bengio, "Practical recommendations for gradient-based training of deep architectures," arXiv.1206.5533, 2012
33. P. Swietojanski, A. Ghoshal, and S. Renals, "Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR," in Proc. IEEE Workshop on Spoken Language Technology, Miami, 2012
34. GE Hinton, S Osindero, and Y Teh, "A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, 2006
35. 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
36. A Mohamed, GE Dahl, and GE Hinton, "Acoustic modeling using deep belief networks," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, 2012
37. GE Hinton, "Products of experts," in Proc. Int. Conf. Artificial Neural Networks (ICANN), 1999, vol. 1, pp. 1-6.