Comparing multilayer perceptron to deep belief network tandem features for robust ASR

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

Volumn , Issue , 2011, Pages 4596-4599

  Vinyals, Oriol ^a,b   Ravuri, Suman V ^a,b  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Automatic Speech Recognition; Deep Belief Network; Multilayer Perceptron

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; HIGH NOISE; MULTILAYER PERCEPTRON; NOISE CONDITIONS; NOISE LEVELS; ROBUST ASR; SINGLE LAYER;

ACOUSTIC NOISE; BAYESIAN NETWORKS; MULTILAYERS; SIGNAL PROCESSING; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 80051644173     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947378     Document Type: Conference Paper

References (11)

1. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem Connectionist Feature Extraction for Conventional HMM Systems," in Proc. ICASSP, 2000.
2. G. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets," Neural Comput., vol. 18, pp. 1527-1554, 2006.
3. A. Mohamed, D. Yu, and L. Deng, "Investigation of Full-Sequence Training of Deep Belief Networks for Speech Recognition," in Proc. Interspeech, 2010.
4. Hynek Hermansky and Sangita Sharma, "Temporal patterns (traps) in asr of noisy speech," in in Proc. ICASSP, 1999, pp. 289-292.
5. Sangita Sharma, Dan Ellis, Sachin Kajarekar, Pratibha Jain, and Hynek Hermansky, "Feature extraction using non-linear transformation for robust speech recognition on the aurora database," in Proc. ICASSP, 2000, pp. 1117-1120.
6. G. Hinton and R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, pp. 504-507, 2006.
7. A. Mohamed, G. Dahl, and G. Hinton, "Deep belief networks for phone recognition," in NIPS Workshop, 2009.
8. L. Deng, M. Seltzer, D. Yu, A. Acero, A. Mohamed, and G. Hinton, "Binary Coding of Speech Spectrograms Using a Deep Auto-encoder," in Proc. Interspeech, 2010.
9. Y. Bengio, "Learning deep architectures for AI," Foundations and Trends in Machine Learning, vol. 2, no. 1, pp. 1-127, 2009.
10. H.G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in ISCA ITRW ASR: Challenges for the Next Millennium, 2000.
11. "Quicknet," http://www.icsi.berkeley.edu/Speech/qn.html.