Neural network acoustic models for the DARPA RATS program

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

Volumn , Issue , 2013, Pages 3092-3096

  Soltau, Hagen ^a   Kuo, Hong Kwang ^a   Mangu, Lidia ^a   Saon, George ^a   Beran, Tomas ^a  

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

Author keywords

Convolutional neural network; Multi layer perceptron; Time delay neural network

Indexed keywords

NEURAL NETWORKS;

CONVOLUTIONAL NEURAL NETWORK; ERROR RATE REDUCTION; GAUSSIAN MIXTURE MODEL (GMMS); MULTI LAYER PERCEPTRON; MULTI-LAYER PERCEPTRONS (MLPS); SPOKEN TERM DETECTION (STD); SPOKEN TERM DETECTIONS; TIME DELAY NEURAL NETWORKS;

RATS;

EID: 84906257050     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. F. Seide, G. Li, and D. Yu, "Conversational speech transcription using context-dependent deep neural networks, " in Interspeech, 2011.
2. H. Bourlard and N. Morgan, Connectionist Speech Recogniton, A Hybrid Approach. Kluwer, 1994.
3. G. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets, " in Neural Computation, 2006.
4. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription, " in Proc. ASRU, 2011.
5. D. Rumelhart, G. Hinton, and R. Williams, "Learning internal representations by error propagation, " in Parallel Distributed Processing, 1986.
6. M. Maamouri et al., "LDC2006S29, Arabic CTS Levantine QT training data set 5, " in Linguistic Data Consortium, 2006.
7. D. Graff, S. Sessa, S. Strassel, and K.Walker, "Rats data plan, " in Linguistic Data Consortium, Tech. Rep., 2011.
8. H. Soltau, G. Saon, B. Kingsbury, H.-K. Kuo, L. Mangu, D. Povey, and A. Emami, "Advances in Arabic Speech Transcription at IBM under the DARPA GALE Program, " IEEE TSAP, 2009.
9. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for model and featurespace discriminative training, " in Proc. ICASSP, vol. II., 2008, pp. 4057-4060.
10. L.Mangu, H. Soltau, H.-K. Kuo, B. Kingsbury, and G. Saon, "Exploiting diversity for spoken term detection, " in Proc. ICASSP, 2013.
11. X. Glorot and Y. Bengio, "Understanding the difficulty of training deep feedforward neural networks, " in Proc. AISTATS, 2010, pp. 249-256.
12. T. Sainath, B. Kingsbury, B. Ramabhadran, P. Fousek, P. Novak, and A. Mohamed, "Making deep belief networks effective for large vocabulary continuous speech recognition, " in Proc. ASRU, 2011, submitted.
13. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition, " in ICASSP-2005, 2005.
14. M. Athineos and D. Ellis, "Autoregressive modelling of temporal envelopes, " IEEE Transactions on Signal Processing, vol. 55, no. 11, 2007.
15. S. Ganapathy, "Signal analysis using autoregressive models of amplitude modulaton, " Ph.D. dissertation, Johns Hopkins University, 2012.
16. B. Kingsbury, "Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling, " in Proc. ICASSP, 2009.
17. 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.
18. J. Martens, "Deep learning via Hessian-free optimization, " in Proc. ICML, 2010.
19. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. Lang, "Phoneme recognition: Neural networks vs hidden Markov models, " in Proc. ICASSP, 1988.
20. Y. L. 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.
21. O. Abdel-Hamid, A. Mohamed, H. Jiang, and G. Penn, "Applying convolutional neural network concepts to hybrid NN-HMM model for speech recognition, " in Proc. ICASSP, 2012.
22. T. Sainath, A. Mohamed, b. Kingsbury, and B. Ramabhadran, "Deep convolutional neural networkds for LVCSR, " in Proc. Interspeech, 2013.