A cluster-based multiple deep neural networks method for large vocabulary continuous speech recognition

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

Volumn , Issue , 2013, Pages 6650-6654

  Zhou, Pan ^a   Liu, Cong ^b   Liu, Qingfeng ^b   Dai, Lirong ^a   Jiang, Hui ^c  

^a National Engineering Laboratory for Speech and Language Information Processing   (China)

^b UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

^c YORK UNIVERSITY   (Canada)

Author keywords

cluster based multi DNN; DNN; LVCSR; parallelization among GPUs; state clustering

Indexed keywords

CLUSTER-BASED; DNN; LVCSR; PARALLELIZATIONS; STATE CLUSTERING;

CONTINUOUS SPEECH RECOGNITION; PROGRAM PROCESSORS; SIGNAL PROCESSING;

NEURAL NETWORKS;

EID: 84890496567     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638948     Document Type: Conference Paper

References (20)

1. H. Bourlard and N. Morgan, Connectionist Speech Recogni-tion: A Hybrid Approach, Kluwer Academic Publishers, 1993.
2. Li Deng, "An overview of deep-structured learning for infor-mation processing," in Proc. of Asian-Pacific Signal and Infor-mation Processing-Annual Summit and Conference (APSIPA-ASC), 2011.
3. D. Yu and L. Deng, "Deep learning and its applications to signal and information processing," IEEE Signal Processing Magazine, vol. 28, pp. 145-154, 2011.
4. G. E. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, et al., "Deep neural networks for acoustic modeling in speech recognition," IEEE Signal Processing Magazine, vol. 29, pp. 82-97, 2012.
5. A. Mohamed, G. Dahl, and G. Hinton, "Acoustic modeling using deep belief networks," IEEE Trans. on Audio, Speech and Language Processing, January 2012.
6. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pre-trained deep neural networks for large vocabulary speech recognition," IEEE Trans. on Audio, Speech and Language Processing, pp. 30-42, January 2012.
7. F. Seide, G. Li, and D. Yu, "Conversational speech transcrip-tion using context-dependent deep neural networks," in Inter-speech, 2011, pp. 437-440.
8. G.E. Dahl, D. Yu, L. Deng, and A. Acero, "Large vocab-ulary continuous speech recognition with context-dependent dbn-hmms," in ICASSP, 2011.
9. J. Pan, C. Liu, Z. Wang, Y. Hu, and H. Jiang, "Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMs in acoustic modelling," in The 8th International Symposium on Chinese Spoken Language Processing (ISCSLP-2012), 2012.
10. Q. Zhu, A. Stolcke, B.Y. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system," in Interspeech, 2005, pp. 2141-2144.
11. G. E. Hinton, S. Osindero, and Y.W. Teh, "A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, pp. 1527-1554, 2006.
12. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, "Greedy layer-wise training of deep networks," in NIPS'06, 2006, pp. 153-160.
13. S. Scanzio, S. Cumani, R. Gemello, F. Mana, and P. Laface, "Parallel implementation of artificial neural network training," in ICASSP, 2010.
14. N. Jaitly, P. Nguyen, A. Senior, and V. Vanhoucke, "Appli-cation of pretrained deep neural networks to large vocabulary speech recognition," in Interspeech, 2012.
15. Stanislav Kontar, "Parallel training of neural networks for speech recognition," in 12th International Conference on Soft Computing MENDEL, 2006.
16. K. Vesely, L. Burget, and F. sek Grezl, "Parallel training of neural networks for speech recognition," in Interspeech, 2010.
17. J. Park, F. Diehl, M.J.F. Gales, M. Tomalin, and P.C. Wood-land, "Efficient generation and use of MLP features for arabic speech recognition," in Interspeech, 2009.
18. Q.V. Le, M.A. Ranzato, R. Monga, M. Devin, K. Chen, G.S. Corrado, J. Dean, and A.Y. Ng, "Building high-level features using large scale unsupervised learning," in ICML, 2012.
19. X. Chen, A. Eversole, G. Li, D. Yu, and F. Seide, "Pipelined back-propagation for context-dependent deep neural network-s," in Interspeech, 2012.
20. P. Farber, "Quicknet on multispert: Fast parallel neural net-work training," Tech. Rep., ICSI, 1997.