Modeling long temporal contexts in convolutional neural network-based phone recognition

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

Volumn 2015-August, Issue , 2015, Pages 4575-4579

  Toth, Laszlo ^a  

^a UNIVERSITY OF SZEGED   (Hungary)

Author keywords

convolutional neural network; Deep neural network; maxout; split temporal context; TIMIT

Indexed keywords

AUDIO SIGNAL PROCESSING; CONVOLUTION; NEURAL NETWORKS; SPEECH COMMUNICATION; SPEECH RECOGNITION; TELEPHONE SETS;

CONVOLUTIONAL NEURAL NETWORK; MAXOUT; PHONE ERROR RATE; PHONE RECOGNITION; RELATIVE ERROR RATES; SPEECH RECOGNIZER; SPLIT TEMPORAL CONTEXT; TIMIT;

DEEP NEURAL NETWORKS;

EID: 84946020232     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178837     Document Type: Conference Paper

References (26)

1. T. N. Sainath, A. Mohamed, B. Kingsbury, and B. Ramabhadran, Deep convolutional neural networks for LVCSR, in Proc. ICASSP, 2013, pp. 8614-8618
2. A. Mohamed, G. E. Dahl, and G. Hinton, Acoustic modeling using deep belief networks, IEEE Trans. ASLP, vol. 20, no. 1, pp. 14-22, 2012
3. M. D. Zeiler, M. Ranzato, R. Monga, M. Mao, K. Yang, Q. V. Le, P. Nguyen, A. Senior, V. Vanhoucke, J. Dean, and G. E. Hinton, On rectified linear units for speech processing, in Proc. ICASSP, 2013, pp. 3517-3521
4. N. Morgan, Deep and wide: Multiple layers in automatic speech recognition, IEEE Trans. ASLP, vol. 20, no. 1, pp. 7-13, 2012
5. J. Pan, C. Liu, Z. G. Wang, Y. Hu, and H. Jiang, Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMs in acoustic modeling, in Proc. ISCSLP, 2012, pp. 301-305
6. A. Janin, D. Ellis, and N.Morgan, Multi-stream speech recognition: Ready for prime time?, in Proc. Eurospeech, 1999, pp. 591-594
7. L. Tóth, Combining time-and frequency-domain convolution in convolutional neural network-based phone recognition, in Proc. ICASSP, 2014, pp. 190-194
8. O. Abdel-Hamid, A. Mohamed, H. Jiang, and G. Penn, Applying convolutional neural network concepts to hybrid NN-HMM model for speech recognition, in Proc. ICASSP, 2012, pp. 4277-4280
9. H. Bourlard and N. Morgan, Connectionist Speech Recognition-A Hybrid Approach, Kluwer, 1994
10. P. Scanlon, D. P. W. Ellis, and R. Reilly, Using mutual information to design class-specific phone recognizers, in Proc. Interspeech, 2003, pp. 857-860
11. J. Pinto et al., Analysis of MLP based hierarchical phoneme posterior probability estimator, IEEE Trans. ASLP, vol. 19, no. 2, pp. 225-241, 2010
12. Vasquez, D. and Gruhn, R. and Minker, W., Hierarchical Neural Network Structures for Phoneme Recognition, Springer, 2013
13. Y. Zhang, E. Chuangsuwanich, and J. Glass, Language ID-based training of multilingual stacked bottleneck features, in Proc. Interspeech, 2014, pp. 1-5
14. K. Vesel ý, M. Karafiát, and F. Grézl, Convolutive bottleneck network features for LVCSR, in Proc. ASRU, 2011, pp. 42-47
15. L. Tóth, Convolutional deep rectifier neural nets for phone recognition, in Proc. Interspeech, 2013, pp. 1722-1726
16. P. Schwarz, P. Matějka, and J. Černocký, Hierarchical structures of neural networks for phoneme recognition, in Proc. ICASSP, 2006, pp. 325-328
17. S. M. Siniscalchi, D. Yu, L. Deng, and C.-H. Lee, Speech recognition using long-span temporal patterns in a deep network model, IEEE Signal Processing Letters, vol. 20, no. 3, pp. 201-204, 2013
18. B. Li and K. C. Sim, Modeling long temporal contexts for robust DNN-based speech recognition, in Proc. Interspeech, 2014, pp. 353-357
19. M. Baccouche, B. Besset, P. Collen, and O. Le Blouch, Deep learning of split temporal context for automatic speech recognition, in Proc. ICASSP, 2014, pp. 5459-5463
20. O. Abdel-Hamid, L. Deng, and D. Yu, Exploring convolutional neural network structures and optimization techniques for speech recognition, in Proc. Interspeech, 2013, pp. 3366-3370
21. T. N. Sainath, B. Kingsbury, A. Mohamed, and B. Ramabhadran et al., Improvements to deep convolutional neural networks for LVCSR, in Proc. ASRU, 2013, pp. 315-320
22. L. Tóth, Convolutional deep maxout networks for phone recognition, in Proc. Interspeech, 2014, pp. 1078-1082
23. H. Ketabdar and H. Bourlard, Enhanced phone posteriors for improving speech recognition systems, IEEE Trans. ASLP, vol. 18, no. 6, pp. 1094-1106, 2010
24. G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, Improving neural networks by preventing co-adaptation of feature detectors, CoRR, vol. abs/1207.0580, 2012
25. V. Peddinti, T N. Sainath, S.Maymon, B. Ramabhadran, D. Nahamoo, and V. Goel, Deep scattering spectrum with deep neural networks, in Proc. ICASSP, 2014, pp. 210-214
26. A. Graves, A. Mohamed, and G. E. Hinton, Speech recognition with deep recurrent neural networks, in Proc. ICASSP, 2013, pp. 6645-6649