G Hinton, L Deng, D Yu, GE Dahl, A Mohamed, N Jaitly, A Senior, V Vanhoucke, P Nguyen, TN Sainath, B Kingsbury, Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Proc. Mag.29(6), 82–97 (2012).
Article
Google Scholar
B Kingsbury, in Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling. Acoustics, Speech and Signal Processing (ICASSP), 2009 IEEE International Conference On (IEEE. TaipeiTaiwan, 2009), pp. 3761–3764.
Google Scholar
K Veselỳ, A Ghoshal, L Burget, D Povey, in INTERSPEECH. Sequence-discriminative training of deep neural networks (ISCA. LyonFrance, 2013), pp. 2345–2349.
Google Scholar
F Seide, G Li, X Chen, D Yu, in Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop On. Feature engineering in context-dependent deep neural networks for conversational speech transcription (IEEE. Waikoloa, HIUSA, 2011), pp. 24–29.
Chapter
Google Scholar
SP Rath, D Povey, K Veselỳ, J Cernockỳ, in INTERSPEECH. Improved feature processing for deep neural networks (ISCA. LyonFrance, 2013), pp. 109–113.
Google Scholar
TN Sainath, B Kingsbury, B Ramabhadran, P Fousek, P Novak, A Mohamed, in Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop On. Making deep belief networks effective for large vocabulary continuous speech recognition (IEEE. Waikoloa, HIUSA, 2011), pp. 30–35.
Chapter
Google Scholar
MJ Gales, Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Lang.12(2), 75–98 (1998).
Article
Google Scholar
G Saon, H Soltau, D Nahamoo, M Picheny, in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop On. Speaker adaptation of neural network acoustic models using i-vectors (IEEE. OlomoucCzech Republic, 2013), pp. 55–59.
Chapter
Google Scholar
A Senior, I Lopez-Moreno, in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference On. Improving DNN speaker independence with i-vector inputs (IEEE. FlorenceItaly, 2014), pp. 225–229.
Chapter
Google Scholar
ML Seltzer, D Yu, Y Wang, in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On. An investigation of deep neural networks for noise robust speech recognition (IEEE. VancouverCanada, 2013), pp. 7398–7402.
Chapter
Google Scholar
TN Sainath, B Kingsbury, G Saon, H Soltau, A Mohamed, GE Dahl, B Ramabhadran, Deep convolutional neural networks for large-scale speech tasks. Neural Netw (2014). in press.
L Deng, JC Platt, in INTERSPEECH. Ensemble deep learning for speech recognition (ISCASingapore, 2014), pp. 1915–1919.
Google Scholar
X Zeng, TR Martinez, Using a neural network to approximate an ensemble of classifiers. Neural. Process. Lett.12(3), 225–237 (2000).
Article
MATH
Google Scholar
C Buciluă, R Caruana, A Niculescu-Mizil, in Knowledge Discovery and Data Mining, The 12th ACM SIGKDD International Conference On. Model compression (ACM. Philadelphia, PAUSA, 2006), pp. 535–541.
Chapter
Google Scholar
J Li, R Zhao, JT Huang, Y Gong, in INTERSPEECH. Learning small-size DNN with output-distribution-based criteria (ISCASingapore, 2014), pp. 1910–1914.
Google Scholar
GE Hinton, O Vinyals, J Dean, in NIPS Deep Learning and Representation Learning Workshop. Distilling the knowledge in a neural network (NIPS. MontrealCanada, 2014).
Google Scholar
H Bourlard, Y Konig, N Morgan, in EUROSPEECH. Remap: recursive estimation and maximization of a posteriori probabilities in connectionist speech recognition (ISCAMadrid, Spain, 1995).
Google Scholar
Y Konig, H Bourlard, N Morgan, in Acoustics, Speech and Signal Processing (ICASSP), 1996 IEEE International Conference On. Remap-experiments with speech recognition (IEEE. Atlanta, GAUSA, 1996), pp. 3350–3353.
Chapter
Google Scholar
A Senior, T Robinson, in Advances in Neural Information Processing Systems (NIPS). Forward-backward retraining of recurrent neural networks (NIPSDenver, CO, USA, 1996), pp. 743–749.
Google Scholar
Y Yan, M Fanty, R Cole, in Acoustics, Speech and Signal Processing (ICASSP), 1997 IEEE International Conference On. Speech recognition using neural networks with forward-backward probability generated targets (IEEE. MunichGermany, 1997), pp. 3241–3244.
Google Scholar
K Veselỳ, M Hannemann, L Burget, in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop On. Semi-supervised training of deep neural networks (IEEE. OlomoucCzech Republic, 2013), pp. 267–272.
Chapter
Google Scholar
F Grézl, M Karafiát, in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop On. Semi-supervised bootstrapping approach for neural network feature extractor training (IEEE. OlomoucCzech Republic, 2013), pp. 470–475.
Chapter
Google Scholar
J Menke, A Peterson, M Rimer, T Martinez, in Neural Networks (IJCNN), 2002 International Joint Conference On. Network simplification through oracle learning (IEEE. Honolulu, HIUSA, 2002), pp. 2482–2486.
Google Scholar
J Ba, R Caruana, in Advances in Neural Information Processing Systems (NIPS). Do deep nets really need to be deep? (NIPS. MontrealCanada, 2014), pp. 2654–2662.
Google Scholar
Y Miao, L Jiang, H Zhang, F Metze, in Spoken Language Technology (SLT), 2014 IEEE Workshop On. Improvements to speaker adaptive training of deep neural networks (IEEESouth Lake Tahoe, NV, USA, 2014), pp. 165–170.
Chapter
Google Scholar
W Chan, NR Ke, I Lane, in INTERSPEECH. Transferring knowledge from a RNN to a DNN (ISCA. DresdenGermany, 2015), pp. 3264–3268.
Google Scholar
D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, M Hannemann, P Motlicek, Y Qian, P Schwarz, J Silovsky, G Stemmer, K Vesely, in Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop On. The Kaldi speech recognition toolkit (IEEEWaikoloa, HI, USA, 2011), pp. 1–4.
Google Scholar
H Soltau, H-K Kuo, L Mangu, G Saon, T Beran, in INTERSPEECH. Neural network acoustic models for the DARPA RATS program (ISCALyon, France, 2013), pp. 3092–3096.
Google Scholar
MJF Gales, DY Kim, PC Woodland, HY Chan, D Mrva, R Sinha, SE Tranter, Progress in the CU-HTK broadcast news transcription system. IEEE Tran. Audio Speech Lang. Process.14(5), 1513–1525 (2006).
Article
Google Scholar
G Saon, G Zweig, B Kingsbury, L Mangu, U Chaudhari, in EUROSPEECH. An architecture for rapid decoding of large vocabulary conversational speech (ISCA. GenevaSwitzerland, 2003), pp. 1977–1980.
Google Scholar
Y Li, H Erdogan, Y Gao, E Marcheret, in INTERSPEECH. Incremental on-line feature space mllr adaptation for telephony speech recognition (ICSADenver, CO, USA, 2002), pp. 1417–1420.
Google Scholar
X Lei, H Lin, G Heigold, in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On. Deep neural networks with auxiliary gaussian mixture models for real-time speech recognition (IEEEVancouver, Canada, 2013), pp. 7634–7638.
Chapter
Google Scholar
M Bacchiani, in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On. Rapid adaptation for mobile speech applications (IEEEVancouver, Canada, 2013), pp. 7903–7907.
Chapter
Google Scholar
V Vanhoucke, A Senior, MZ Mao, in NIPS Deep Learning and Unsupervised Feature Learning Workshop. Improving the speed of neural networks on cpus (NIPSGranada, Spain, 2011).
Google Scholar
X Lei, A Senior, A Gruenstein, J Sorensen, in INTERSPEECH. Accurate and compact large vocabulary speech recognition on mobile devices (ISCA. LyonFrance, 2013), pp. 662–665.
Google Scholar
V Vanhoucke, M Devin, G Heigold, in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On. Multiframe deep neural networks for acoustic modeling (IEEEVancouver, Canada, 2013), pp. 7582–7585.
Chapter
Google Scholar
D Yu, F Seide, G Li, L Deng, in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference On. Exploiting sparseness in deep neural networks for large vocabulary speech recognition (IEEEKyoto, Japan, 2012), pp. 4409–4412.
Chapter
Google Scholar
TN Sainath, B Kingsbury, V Sindhwani, E Arisoy, B Ramabhadran, in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On. Low-rank matrix factorization for deep neural network training with high-dimensional output targets (IEEEVancouver, Canada, 2013), pp. 6655–6659.
Chapter
Google Scholar
J Xue, J Li, Y Gong, in INTERSPEECH. Restructuring of deep neural network acoustic models with singular value decomposition (ISCALyon, France, 2013), pp. 2365–2369.
Google Scholar
T He, Y Fan, Y Qian, T Tan, K Yu, in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference On. Reshaping deep neural network for fast decoding by node-pruning (IEEEFlorence, Italy, 2014), pp. 245–249.
Chapter
Google Scholar
J Ramirez, JM Górriz, JC Segura, in Robust Speech Recognition and Understanding, ed. by M Grimm, K Kroschel. Voice activity detection. Fundamentals and speech recognition system robustness (I-Tech Education and PublishingVienna, 2007), pp. 1–22.
Google Scholar
J Dines, J Vepa, T Hain, in INTERSPEECH. The segmentation of multi-channel meeting recordings for automatic speech recognition (ICSLPPittsburgh, PA, USA, 2006).
Google Scholar
G Saon, S Thomas, H Soltau, S Ganapathy, B Kingsbury, in INTERSPEECH. The IBM speech activity detection system for the DARPA RATS program (ISCALyon, France, 2013), pp. 3497–3501.
Google Scholar
S Thomas, S Ganapathy, G Saon, H Soltau, in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference On. Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions (IEEEFlorence, Italy, 2014), pp. 2519–2523.
Chapter
Google Scholar
Y LeCun, L Bottou, Y Bengio, P Haffner, Gradient-based learning applied to document recognition. Proc. IEEE. 86(11), 2278–2324 (1998).
Article
Google Scholar
Y Miao, Kaldi + PDNN: building DNN-based ASR systems with Kaldi and PDNN. arXiv preprint arXiv:1401.6984 (2014).
R Caruana, S Baluja, T Mitchell, in Advances in Neural Information Processing Systems (NIPS). Using the future to “sort out” the present: Rankprop and multitask learning for medical risk evaluation (NIPSDenver, CO, USA, 1996), pp. 959–965.
Google Scholar
M Denil, B Shakibi, L Dinh, MA Ranzato, N de Freitas, in Advances in Neural Information Processing Systems (NIPS). Predicting parameters in deep learning (NIPSLake Tahoe, NV, USA, 2013), pp. 2148–2156.
Google Scholar
H Nobach, C Tropea, L Cordier, JP Bonnet, J Delville, J Lewalle, M Farge, K Schneider, R Adrian, in Springer Handbook of Experimental Fluid Mechanics, 1, ed. by C Tropea, AL Yarin, and JF Foss. Review of some fundamentals of data processing (SpringerHeidelberg, 2007), pp. 1337–1398.
Chapter
Google Scholar
H Soltau, G Saon, TN Sainath, in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference On. Joint training of convolutional and non-convolutional neural networks, (2014), pp. 5572–5576.
Chapter
Google Scholar