Time-frequency kernel-based CNN for speech recognition

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2015-January, Issue , 2015, Pages 1888-1892

  Zhao, Tuo ^a   Zhao, Yunxin ^a   Chen, Xin ^b  

^a UNIVERSITY OF MISSOURI   (United States)

^b Pearson Knowledge Technologies   (United States)

Author keywords

Convolutional neural network; Robust speech recognition; Time frequency kernels

Indexed keywords

CONVOLUTION; FREQUENCY DOMAIN ANALYSIS; NEURAL NETWORKS; SPEECH; SPEECH COMMUNICATION; TELEPHONE SETS;

CONVOLUTIONAL NEURAL NETWORK; DIFFERENT TREATMENTS; FREQUENCY DOMAINS; KERNEL APPROACHES; PHONE RECOGNITION; ROBUST SPEECH RECOGNITION; SPEAKER INDEPENDENTS; TIME FREQUENCY KERNELS;

SPEECH RECOGNITION;

EID: 84959087712     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Mohamed, A., Dahl, G. E. and Hinton, G., "Acoustic Modeling Using Deep Belief Networks", IEEE Trans. Audio, Speech, Lang. Proc., 20 (1): 14-22, 2012.
2. Vanhoucke, V., Devin, M. and Heigold, G., "Multiframe deep neural networks for acoustic modeling", in Proc. ICASSP, 7582-7585, 2013.
3. Warren, R. M., "Perceptual processing of speech and other perceptual patterns: Some similarities and differences", in Greenberg S. and Ainsworth, W., Ed. Listening to Speech: An Auditory Perspective, Oxford University Press, 1998.
4. Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G. and Yu, D., "Convolutional Neural Networks for Speech Recognition", IEEE/ACM Trans. Audio, Speech, and Lang. Proc., 22 (10): 1533-1545, 2014.
5. T. N. Sainath, A. Mohamed, B. Kingsbury and B. Ramabhadran, "Deep convolutional neural networks for LVCSR, " in Proc. ICASSP, May 2013.
6. Sainath, T., Kinsbury, B., Mohamed, A. and Ramabhadran, B., "Improvements to deep convolutional neural networks for LVCSR", in Proc. ASRU, 2013.
7. Abdel-Hamid, O., Deng, L. and Yu, D., "Exploring convolutional neural network structures and optimization techniques for speech recognition", in Proc. Interspeech, 3366-3370, 2013.
8. Toth, L., "Convolutional deep rectifier neural nets for phone recognition", in Proc. Interspeech, 1722-1726, 2013.
9. Vesely, K. ; Karafiat, M. ; Grezl, F., "Convolutive Bottleneck Network features for LVCSR, " IEEE Workshop on ASRU, 2011.
10. Toth, L., "Combining time-and frequency-domain convolution in convolutional neural network-based phone recognition", in Proc. ICASSP, 190-194, 2014.
11. Allen, J., "How Do Humans Process and Recognise Speech", IEEE Trans. Speech and Audio Proc., 2 (4): 567-577, 1994.
12. Wu S., Kingsbury B., Mongan N. and Greenberg S., "Incorporating information from syllable-length time scales into automatic speech recognition", in Proc. ICASSP, 721-724, 1998.
13. McCourt, P., Vaseghi, S. and Harte, N., "Multi-resolution cepstral features for phoneme recognition across speech sub-bands", in Proc. ICASSP, 557-560, 1998.
14. "The Computational Network Toolkit (CNTK)", Microsoft Corporation, Redmond, WA, USA. Online: https: //cntk. codeplex. com/SourceControl/latest, accessed on 04 Mar. 2015.
15. https: //catalog. ldc. upenn. edu/docs/LDC96S32/FFMTIMIT. TXT
16. LeCun, Y. and Bengio Y., "Convolutional networks for images, speech and time series", in Arbib, M. A., Ed., The Handbook of Brain Theory and Neural Networks, MIT Press, 255-258, 1995.
17. Abdel-Hamid, O., Mohamed, A., Jiang, H. and Penn, G., "Applying convolutional neural network concepts to hybrid NNHMM models for speech recognition", in Proc. ICASSP, 4277-4280, 2012.
18. Lee, K. and Hon, H., "Speaker-Independent Phone Recognition Using Hidden Markov Models", IEEE Trans. Audio, Speech, Signal Proc. 37 (11): 1641-1648, 1989.
19. "The Hidden Markov Model Toolkit (HTK)", CUED Machine Intelligence Lab. Cambridge, UK. Online: http: //htk. eng. cam. ac. uk/ftp/software/HTK-3. 4. 1. Tar. gz, accessed on 28 Jun. 2013.
20. Vesely, K., Burget, L. and Grezl, F., "Parallel training of neural networks for speech recognition", in Proc. International Conf. Text, Speech and Dialog, 439-446, 2010.