Investigating deep neural network based transforms of robust audio features for LVCSR

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

Volumn , Issue , 2013, Pages 6709-6713

  Bocchieri, Enrico ^a   Dimitriadis, Dimitrios ^a  

^a AT AND T LABS RESEARCH   (United States)

Author keywords

feature extraction; Neural networks; robustness; speech recognition

Indexed keywords

AUDIO FEATURES; CEPSTRAL FEATURES; DEEP NEURAL NETWORKS; FEATURE TRANSFORM; FORMANT FREQUENCY; FREQUENCY MEASURES; LARGE VOCABULARY; RELATIVE ERROR RATES;

FEATURE EXTRACTION; MODULATION; NEURAL NETWORKS; ROBUSTNESS (CONTROL SYSTEMS); SPEECH RECOGNITION;

MATHEMATICAL TRANSFORMATIONS;

EID: 84890543873     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638960     Document Type: Conference Paper

References (25)

1. K. K. Paliwal, "Spectral subband centroid features for speech recognition", in Proc. ICASSP, Seattle, WA, May 1998, pp. 617-620
2. Chia-Ping Chen and J. A. Bilmes, "MVA Processing of Speech Features" IEEE Trans. On Audio, Speech and Lang. Proc. Vol. 15, No. 1, Jan. 2007
3. H. Hermansky and N. Morgan, "RASTA Processing of Speech", IEEE Trans. On Speech and Audio Processing, Vol. 2, No. 4, Oct. 1994
4. G. Saon, M. Padmanabhan, R. Gopinath, and S.Chen, "Maximum likelihood discriminant feature spaces," in Proc. ICASSP-2000, pp. 1129-1132
5. N. Kumar and G. Andreou, "Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition," Speech Communication, vol. 26, pp. 283-297, 1998
6. R.A. Gopinath, "Maximum likelihood modeling with [Gaussian distributions for classifications," in Proc. ICASSP, 1998, pp. 661-664
7. M.J.F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Tech. Rep. CUED/FINFENG/TR291, Cambridge Univ., 1997
8. M. Saraclar, M. Riley, E. Bocchieri, and V. Goffin, Towards automatic closed captioning: low latency real time broadcast news transcriptions", in Proc. International Conference on Spoken Language Processing (ICSLP), Sep. 2002, pp. 741-1744
9. S.B. Davis, P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences", IEEE Trans. on Acoustic, Speech and Signal Processing, 28(4):357-366, 1980
10. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. of Acoust. Soc. of America, vol. 87, no. 4, pp. 1738-1752, 1990
11. H.Hermansky, D. Ellis and S.Sharma, "Tandem connectionist feature stream extraction for conventional HMM systems.", in Proc. of ICASSP-2000, Istanbul, June 2000
12. F. Gre ?zl, M. Karafia ?t, S. Konta ?r and J. Cernocky, "Probabilistic and bottle-neck features for ASR of meetings", in Proc. of ICASSP-2007, pp 757-760
13. P.Fousek, L.Lamel and J.Gauvain, "Transcribing broadcast data using MLP features", in Proc. Interspeech 2008, pp 1433-1436
14. D.Yu and M.L.Seltzer,"Improved Bottleneck Features Using Pretrained Deep Neural Networks", in Proc. Interspeech 2011, pp 237-240
15. T.N.Sainath, B.Kingsbury and B.Ramabhadran,"Auto-encoder bottleneck features using deep belief networks", in Proc. of ICASSP-2012
16. Z.Tüske, R.Schlüter, H. Ney, M.Sundermeyer, "Context-Dependent MLPs for LVCSR: TANDEM, Hybrid or Both?," Proc. INTERSPEECH 2012, Portland, Oregon
17. W. XU, "Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent", last revised 22Dec 2011, arxiv.org/abs/1107. 2490
18. L.Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent", Proceedings of the 19th International Conference on Computational Statistics (COMPSTAT'2010), 177-187, Edited by Yves Lechevallier and Gilbert Saporta, Paris, France, August 2010, Springer
19. M. Riedmiller and H. Braun, "A direct adaptive method for faster backpropagation learning: the RPROP algorithm", in Proc. IEEE International Conference on Neural Networks, 1993, pp 586-591
20. C. Igel and M. Hüsken, "Improving the Rprop Learning Algorithm", in Proc. Of The Second International Symposium On Neural Computation (NC2000)
21. D. Dimitriadis, P. Maragos, and A. Potamianos "Robust AMFM Features for Speech Recognition", IEEE Signal Processing Letters, Vol. 12, No. 9, Sept. 2005
22. A. Potamianos and P. Maragos, "Speech formant frequency and bandwidth tracking using multiband energy demodulation," J. Acoust. Soc.Amer., vol. 99, no. 6, pp. 3795-3806, Jun. 1996
23. E.Bocchieri, D.Caseiro and D.Dimitriadis, "Speech recognition modeling advances for mobile voice search,",in Proc. ICASSP, 2011, pp 4888-4891
24. D.Dimitriadis, E.Bocchieri and D.Caseiro, "An alternative front-end for the AT&T WATSON LV-CSR system", in Proc. ICASSP, 2011
25. D. Dimitriadis and P. Maragos, "Continuous Energy Demodulation Methods and Application to Speech Analysis", Speech Communication, vol.48, no.7, pp.819-837, July 2006.