Joint training of convolutional and non-convolutional neural networks

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

Volumn , Issue , 2014, Pages 5572-5576

  Soltau, Hagen ^a   Saon, George ^a   Sainath, Tara N ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Acoustic Modeling; CNN; MLP; Neural Networks

Indexed keywords

NEURAL NETWORKS;

ACOUSTIC MODEL; ARBITRARY GRAPHS; CNN; CONVOLUTIONAL NEURAL NETWORK; MLP; REGULAR NETWORKS; SIMPLE MODIFICATIONS; SPEECH ACTIVITY DETECTIONS;

SIGNAL PROCESSING;

EID: 84905265980     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854669     Document Type: Conference Paper

References (20)

1. Frank Seide, Gang Li, and Dong Yu, "Conversational speech transcription using context-dependent deep neural networks," in Interspeech, 2011.
2. Y. Le Cun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, "Handwritten digit recognition with a back-propagation network," in Proc. NIPS, 1990.
3. D. Rumelhart, G. Hinton, and R. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing, 1986.
4. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. Lang, "Phoneme recognition: Neural networks vs hidden Markov models," in Proc. ICASSP, 1988.
5. o. Abdel-Hamid, A. Mohamed, H. Jiang, and G. Penn, "Applying convolutional neural network concepts to hybrid NNHMM model for speech recognition," in Proc. ICASSP, 2012.
6. T. Sainath, A. Mohamed, B. Kingsbury, and B. Ramabhadran, "Deep convolutional neural networks for LVCSR," in Proc. ICASSP, 2013.
7. Tara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, George Dahl, George Saon, Hagen Soltau, Tomas Beran, Aleksandr Y. Aravkin, and Bhuvana Ramabhadran, "Improvements to deep convolutional neural networks for LVCSR," in Proc. ASRU, 2013.
8. Qifeng Zhu, Andreas Stolcke, Barry Y. Chen, and Nelson Morgan, "Using MLP features in SRIs conversational speech recognition system," in in Proc. Interspeech, 2005, pp. 21412144.
9. Pavel Golik, Zoltan Tueske, Ralf Schlueter, and Hermann Ney, "Development of the RWTH Transcription System for Slovenian," in Interspeech, Lyon, France, Aug. 2013, pp. 31073111.
10. Hagen Soltau, Hong-Kwang Kuo, Lidia Mangu, George Saon, and Tomas Beran, "Neural Network Acoustic Models for the DARPA RATS Program," in Proc. Interspeech, 2013.
11. Xie Chen, Adam Eversole, Gang Li, Dong Yu, and Frank Seide, "Pipelined back-propagation for context-dependent deep neural networks.," in Proc. INTERSPEECH, 2012.
12. Rich Caruana, "Multitask learning," Machine Learning, vol. 28, no. 1,pp.41-75, 1997.
13. M. Seltzer and J. Droppo, "Multi-task learning in deep neural networks for improved phoneme recognition," in Proc. ICASSP, 2013.
14. Y. Lu, F. Lu, S. Sehgal, S. Gupta, J. Du, C. Tham, P. Green, and V. Wan, "Multitask learning in connectionist speech recognition'" in Proc. ASSTA, 2004.
15. Hagen Soltau, George Saon, and Brian Kingsbury, "The IBM Attila speech recognition toolkit," in Spoken Language Technology Workshop (SLT), 2010 IEEE. IEEE, 2010, pp. 97-102.
16. B. Kingsbury, T. N. Sainath, and H. Soltau, "Scalable minimum Bayes risk training of neural network acoustic models using distributed Hessian-free optimization," in Proc. Interspeech, 2012.
17. N. Dehak, P. Kenny, R. Dehak, P. Dumouchel, and P. Ouellet, "Front-end factor analysis for speaker verification," IEEE Trans. Audio, Speech and Language Processing, vol. 19, no. 4, May 2011.
18. George Saon, Hagen Soltau, David Nahamoo, and Michael Picheny, "Speaker adaptation of neural network acoustic models using I-Vectors," in Proc. ASRU, 2013.
19. Lidia Mangu, Hagen Soltau, Hong-Kwang Kuo, and George Saon, "The IBM Spoken Term Detection System for the DARPA RATS Program," in Proc. ASRU, 2013.
20. George Saon, Samuel Thomas, Hagen Soltau, Sriram Ganapathy, and Brian Kingsbury, "The IBM speech activity detection system for the DARPA RATS program," in Proc. Interspeech, 2013.