Investigation of Deep Neural Networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling

2012 8th International Symposium on Chinese Spoken Language Processing, ISCSLP 2012

Volumn , Issue , 2012, Pages 301-305

  Pan, Jia ^a   Liu, Cong ^a   Wang, Zhiguo ^a   Hu, Yu ^a   Jiang, Hui ^b  

^a IFLYTEK RESEARCH   (China)

^b YORK UNIVERSITY   (Canada)

Author keywords

acoustic modeling; deep neural networks; pre training; speech recognition

Indexed keywords

ACOUSTIC MODELING; CONTEXT DEPENDENT; CONTEXT WINDOW; DEEP NEURAL NETWORKS; FEATURE VECTORS; INPUT FEATURES; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LARGE VOCABULARY SPEECH RECOGNITION; LOGARITHM SPECTRUM; PRE-TRAINING; RELATIVE ERRORS; SPEECH FRAMES; TRAINING DATA;

CONTINUOUS SPEECH RECOGNITION; EXPERIMENTS; SPECTRUM ANALYSIS; SPEECH RECOGNITION; VOCABULARY CONTROL;

NEURAL NETWORKS;

EID: 84874485803     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ISCSLP.2012.6423452     Document Type: Conference Paper

References (9)

1. N. Morgan and H. Bourlard, "Continuous speech recognition using multilayer perceptrons with hidden Markov models," Proc. of ICASSP, 1990.
2. F. Seide, G. Li, and D. Yu, "Conversational speech transcription using context-dependent deep neural networks," Proc. of Interspeech, 2011.
3. H. Jiang, "Discriminative training for automatic speech recognition: A survey", Computer and Speech, Language, pp.589-608, Vol. 24, Issue 4, October 2010.
4. D. Yu, L. Deng, and G. Dahl, "Roles of Pre-training and Fine-Tuning in Context-Dependent DNN-HMMs for Real-World Speech Recognition," Proc. of NIPS Workshop on Deep Learning and Unsupervised Feature Learning, December 2010.
5. F. Seide, G. Li, X. Chen and D. Yu, "Feature Engineering in Context-Dependent Deep Neural Networks for Conversational Speech Transcription," Proc. ASRU 2011, pp. 24-29, 2011.
6. G. Dahl, D. Yu, L. Deng, and A. Acero, "Context-Dependent Pre-Trained Deep Neural Networks for Large Vocabulary Speech Recognition," IEEE Trans. Speech and Audio Proc., Special Issue on Deep Learning for Speech and Language Processing, 2011.
7. G. E. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, pp. 1527-1554, 2006. (Pubitemid 44024729)
8. P. C. Woodland, T. Hain, G. Evermann and D. Povey, "CUHTK March 2001 Hub5 system." Proc. of DARPA Hub5E Conversational Speech Recognition Workshop, 2001.
9. O. Abdel-Hamid, A. Mohamed, H. Jiang and G. Penn, "Applying Convolutional Nerual Networks to Hybrid NN-HMM Model for Speech Recognition," Proc. of ICASSP 2012, Kyoto, Japan, 2012.