Speech acoustic modeling from raw multichannel waveforms

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

Volumn 2015-August, Issue , 2015, Pages 4624-4628

  Hoshen, Yedid ^a   Weiss, Ron J ^b   Wilson, Kevin W ^b  

^a HEBREW UNIVERSITY OF JERUSALEM   (Israel)

^b GOOGLE INC   (United States)

Author keywords

acoustic modeling; Automatic speech recognition; beamforming; convolutional neural networks

Indexed keywords

ACOUSTIC NOISE; AUDIO SIGNAL PROCESSING; BEAMFORMING; CONVOLUTION; DEEP NEURAL NETWORKS; FILTER BANKS; NEURAL NETWORKS; SPEECH; SPEECH COMMUNICATION;

ACOUSTIC MODEL; AUTOMATIC SPEECH RECOGNITION; CONVOLUTIONAL NEURAL NETWORK; FEATURE REPRESENTATION; REVERBERANT CONDITION; SIGNAL IN SPACES; SPATIAL LOCATION; SUPERVISED TRAININGS;

SPEECH RECOGNITION;

EID: 84946030537     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178847     Document Type: Conference Paper

References (20)

1. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton, "Imagenet classification with deep convolutional neural networks, " in NIPS, 2012, pp. 1097-1105
2. Dimitri Palaz, Ronan Coli obert, and Mathew Magimai Doss, "Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks, " Interspeech, 2014
3. Zoltan Ttiske, Pavel Golik, Ralf SchlUter, and Hermann Ney, "Acoustic modeling with deep neural networks using raw time signal for LV CSR, " in Interspeech, Singapore, Sept. 2014
4. Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdelrahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, et aI., "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, " Signal Processing Magazine, IEEE, vol. 29, no. 6, pp. 82-97, 2012
5. Navdeep Jaitly and Geoffrey Hinton, "Learning a better representation of speech soundwaves using restricted Boltzmann machines, " in ICASSP. IEEE, 2011, pp. 5884-5887
6. Keisuke Kinoshita, Marc Delcroix, Takuya Yoshioka, Tomohiro Nakatani, Armin Sehr, Walter Kellermann, and Roland Maas, "The REVERB challenge: A common evaluation framework for dereverberation and recognition of reverberant speech, " in W ASPAA. IEEE, 2013, pp. 1-4
7. Emmanuel Vincent, Jon Barker, Shinji Watanabe, Jonathan Le Roux, Francesco Nesta, and Marco Matassoni, 'The second CHiME speech separation and recognition challenge: Datasets, tasks and baselines, " in ICASSP. IEEE, 2013, pp. 126-130
8. Marc Delcroix, Takuya Yoshioka, Atsunori Ogawa, Yotaro Kubo, Masakiyo Fujimoto, Nobutaka Ito, Keisuke Kinoshita, Miquel Espi, Takaaki Hori, Tomohiro Nakatani, and Atsushi Nakamura, "Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the reverb challenge, " in REVERB Workshop, 2014
9. Zhaozhang Jin and DeLiang Wang, "Reverberant speech segregation based on multipitch tracking and classification, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 8, pp. 2328-2337, 2011
10. Jacob Benesty, Jingdong Chen, and Yiteng Huang, Microphone Array Signal Processing, Springer, 2008
11. Tara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, and Bhuvana Ramabhadran, "Learning filter banks within a deep neural network framework, " in ASRU. IEEE, 2013, pp. 297-302
12. Satoshi Imai, "Cepstral analysis synthesis on the mel frequency scale, " in ICASSP. IEEE, 1983, vol. 8, pp. 93-96
13. Pawel Swietojanski, Arnab Ghoshal, and Steve Renals, "Hybrid acoustic models for distant and multichannel large vocabulary speech recognition, " in ASRU. IEEE, 2013, pp. 285-290
14. Pawel Swietojanski, Arnab Ghoshal, and Steve Renals, "Convolutional neural networks for distant speech recognition, " Signal Processing Letters, 2014
15. Vinod Nair and Geoffrey E Hinton, "Rectified linear units improve restricted Boltzmann machines, " in Proceedings of the 27th International Conference on Machine Learning (ICML-JO), 2010, pp. 807-814
16. Ralf SchlUter, Ilja Bezrukov, Hermann Wagner, and Hermann Ney, "Gammatone features and feature combination for large vocabulary speech recognition, " in ICASSP. IEEE, 2007, vol. 4, pp. IV-649
17. Johan Schalkwyk, Doug Beeferman, Franóise Beaufays, Bill Byrne, Ciprian Chelba, Mike Cohen, Maryam Kamvar, and Brian Strope, "Your Word is my Command: Google search by voice: A case study, " in Advances in Speech Recognition, pp. 61-90. Springer, 2010
18. Stephen G McGovern, "A model for room acoustics, " http://www.sgm-audio.com/research/rir/ rir. html, 2003
19. Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Andrew Senior, Paul Tucker, Ke Yang, Quoc V Le, et aI., "Large scale distributed deep networks, " in NIPS, 2012, pp. 1223-1231
20. John Duchi, Elad Hazan, and Yoram Singer, "Adaptive subgradient methods for online learning and stochastic optimization, " T he lournal of Machine Learning Research, vol. 12, pp. 2121-2159, 2011