Binary coding of speech spectrograms using a deep auto-encoder

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 1692-1695

  Deng, L ^a   Seltzer, M ^a   Yu, D ^a   Acero, A ^a   Mohamed, A ^b   Hinton, G ^b  

^a MICROSOFT RESEARCH   (United States)

^b UNIVERSITY OF TORONTO   (Canada)

Author keywords

Auto encoder; Binary codes; Boltzmann machine; Deep learning; Neural networks; Speech feature extraction

Indexed keywords

BACKPROPAGATION; BINARY CODES; DEEP LEARNING; DEEP NEURAL NETWORKS; LEARNING SYSTEMS; NEURAL NETWORKS; SIGNAL ENCODING; SPECTROGRAPHS; SPEECH; SPEECH COMMUNICATION; VECTOR QUANTIZATION; NETWORK CODING;

AUTO ENCODERS; BOLTZMANN MACHINES; CONTRASTIVE DIVERGENCE; GENERATIVE MODEL; LEARNING STRATEGY; LOG SPECTRAL DISTORTIONS; SPEECH FEATURES; SPEECH SPECTROGRAM; DEEP LEARNING; FEATURES EXTRACTION; LAYER BY LAYER; NEURAL-NETWORKS; SPEECH FEATURE EXTRACTION;

SPEECH RECOGNITION;

EID: 79959842828     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Baker, J., et. al. "Research developments and directions in speech recognition and understanding," IEEE Sig. Proc. Mag., vol. 26, May 2009, pp. 75-80.
2. Baker, J., et. al. "Updated MINDS report on speech recognition and understanding," IEEE Sig. Proc. Mag., July 2009, vol. 26, pp. 78-85.
3. Bell, G., Fujisaki, H., Heinz, J., Stevens, K., and House, A. "Reduction of speech spectra by analysis-by synthesis techniques," J. Acoust. Soc. Am., vol. 33, 1961, pp. 1725-1736.
4. Deng, L. "Computational Models for Speech Production," chapter in Computational Models of Speech Pattern Processing, pp. 199-213, Springer, 1999.
5. Deng, L., Yu, D., and Acero, A. "Structured speech modeling," IEEE Trans. Audio, Speech & Language Proc., vol. 14, no. 5, pp. 1492-1504, September 2006.
6. Halle, M. and Stevens, K. "Speech recognition: A model and program for research," IRE Trans. Information Theory, 1962.
7. He, X., Deng, L., Chou, W. "Discriminative Learning in Sequential Pattern Recognition - A Unifying Review for Optimization-Oriented Speech Recognition," IEEE Sig. Proc. Mag., vol. 25, 2008, pp. 14-36.
8. Hinton, G., Osindero, S., and Teh, Y. "A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, pp. 1527-1554, 2006. (Pubitemid 44024729)
9. Hinton, G. and Salakhutdinov, R. "Reducing the dimensionality of data with neural networks," Science, vol. 313. no. 5786, pp. 504 - 507, July 2006. (Pubitemid 44148451)
10. Mohamed, A., Dahl, G., Hinton, G. "Deep belief networks for phone recognition, "Proc. NIPS Workshop, Dec. 2009.
11. Mohamed, A., Yu, D., and Deng, L. "Investigation of full-sequence training of deep belief networks for speech recognition," Proc. Interspeech, Sept. 2010.
12. Salakhutdinov R. and Hinton, G. "Semantic hashing," Proc. SIGIR Workshop on Information Retrieval and Applications of Graphical Models, 2007.
13. Yu, D., Deng, L., Gong, Y. and Acero, A. "A novel framework and training algorithm for variable-parameter hidden Markov models," IEEE Trans. Audio, Speech and Language Processing, vol. 17, 2009, pp. 1348-1360.
14. Yu, D. and Deng, L. "Solving nonlinear estimation problems using Splines," IEEE Sig. Proc. Mag., vol. 26, 2009, pp. 86-90.
15. Yu, D. and Deng, L. "Deep-structured hidden conditional random fields for phonetic recognition," Proc. Interspeech, Sept. 2010.
16. Yu, D., Deng, L., and Wang, S., "Learning in the deep-structured conditional random fields," Proc. NIPS Workshop, Dec. 2009.
17. Yu, D., Wang, S., Karam, Z., Deng, L. "Language recognition using deep-structured conditional random fields," Proc. ICASSP, April 2010, pp. 5030-5033.