Architectures for deep neural network based acoustic models defined over windowed speech waveforms

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

Volumn 2015-January, Issue , 2015, Pages 6-10

  Bhargava, Mayank ^a   Rose, Richard ^a,b  

^a MCGILL UNIVERSITY   (Canada)

^b GOOGLE INC   (United States)

Author keywords

Bottleneck features; Deep Neural Networks; Speech Recognition; Waveform Speech

Indexed keywords

NETWORK ARCHITECTURE; SPEECH; SPEECH COMMUNICATION;

AUTOMATIC SPEECH RECOGNITION; BOTTLENECK FEATURES; DEEP NEURAL NETWORKS; INTERNAL REPRESENTATION; SPEECH WAVEFORMS; TIME-DOMAIN SIGNAL; WALL STREET JOURNAL; WAVE FORMS;

SPEECH RECOGNITION;

EID: 84959098603     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. D. Palaz, R. Collobert, and M. Magimai.-Doss, "Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks, " in Proc. Interspeech, Lyon, France, Aug. 2013, pp. 1766-1770.
2. Z. Tüske, P. Golik, R. Schlüter, and H. Ney, "Acoustic modeling with deep neural networks using raw time signal for LVSCR, " in Interspeech, Singapore, Sept. 2014, pp. 890-894.
3. Hoshen, Yedid, Ron J. Weiss, and Kevin W. Wilson. "Speech acoustic modelling in raw multichannel waveforms. " in Proc. ICASSP, 2015.
4. S. Furui, "On the role of spectral transition for speech perception", J. Acoust. Soc. Am Vol. 80, No. 4, pp. 1016-1025, 1986.
5. H. Hermansky "Modulation spectrum in speech processing. " Signal Analysis and Prediction. Birkhäuser Boston, 1998. 395-406.
6. A. Mohamed, G. Hinton, and G. Penn, "Understanding how deep belief networks perform acoustic modelling, " in ICASSP, 2012.
7. D. Yu and M. L. Seltzer, "Improved bottleneck features using pretrained deep neural networks", in Proc. Interspeech 2011, pp. 237-240.
8. D. B. Paul and J. M. Baker, "The design for the Wall Street Journal-based CSR corpus, " in Proceedings of the workshop on Speech and Natural Language. Association for Computational Linguistics, 1992, pp. 357362.
9. D. Povey, A. Ghoshal, et al., "The kaldi speech recognition toolkit, " in Proc. ASRU, 2011
10. F. Grézl and P. Fousek, "Optimizing bottle-neck features for LVCSR, " in Proc. ICASSP, 2008
11. F. Grézl and M. Karafiát, "Hierarchical neural net architectures for feature extraction in ASR, " in Proc. INTERSPEECH, 2010, pp. 1201-1204.
12. J. Gehring, W. Lee, K. Kilgour, I. Lane, Y. Miao, and A. Waibel, "Modular combination of deep neural networks for acoustic modeling, " in Proc. Interspeech, pp. 94-98, 2013
13. T. N. Sainath, B. Kingsbury, A. Mohamed, and B. Ramabhad-ran, "Learning filter banks within a deep neural network framework, " in Proc. of ASRU, 2013