Learning small-size DNN with output-distribution-based criteria

Keywords

Computer science, Artificial intelligence

References

• Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech RecognitionDong Yu, Li Deng, George E. Dahl — 2010
• Improving the speed of neural networks on CPUsVincent Vanhoucke, Andrew Senior, M. Mao — 2011
• Recent advances in deep learning for speech research at MicrosoftLi Deng, Jinyu Li, Jui-Ting Huang — 2013
• Error back propagation for sequence training of Context-Dependent Deep NetworkS for conversational speech transcriptionHang Su, Gang Li, Dong Yu — 2013
• Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targetsTara N. Sainath, Brian Kingsbury, Vikas Sindhwani — 2013
• Making Deep Belief Networks effective for large vocabulary continuous speech recognitionTara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran — 2011
• Equivalence of Generative and Log-Linear ModelsGeorg Heigold, Hermann Ney, Patrick Lehnen — 2011
• Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionGeorge E. Dahl, Dong Yu, Li Deng — 2012
• Tree-based state tying for high accuracy acoustic modellingS.J. Young, J. J. Odell, Philip C. Woodland — 1994
• Model compressionCristian Buciluǎ, Rich Caruana, Alexandru Niculescu-Mizil — 2006
• Restructuring of deep neural network acoustic models with singular value decompositionJian Xue, Jinyu Li, Yifan Gong — 2013
• Accurate and compact large vocabulary speech recognition on mobile devicesXin Lei, Andrew Senior, Alexander Gruenstein — 2013
• Application of Pretrained Deep Neural Networks to Large Vocabulary Speech RecognitionNavdeep Jaitly, Patrick Nguyen, Andrew Senior — 2012
• Do Deep Nets Really Need to be Deep?Jimmy Ba, Rich Caruana — 2013
• Variable-component deep neural network for robust speech recognitionRui Zhao, Jinyu Li, Yifan Gong — 2014
• Multiframe deep neural networks for acoustic modelingVincent Vanhoucke, Matthieu Devin, Georg Heigold — 2013
• DEEP NEURAL NETWORKS FOR ACOUSTIC MODELINGVincent Vanhoucke, M. Devin, G. Heigold — 2013

Cited by

• An analysis of convolutional neural networks for speech recognitionJui-Ting Huang, Jinyu Li, Yifan Gong — 2015
• Recurrent neural network training with dark knowledge transferZhiyuan Tang, Dong Wang, Zhiyong Zhang — 2015
• Small-footprint high-performance deep neural network-based speech recognition using split-VQYongqiang Wang, Jinyu Li, Yifan Gong — 2015
• Distilling the Knowledge in a Neural NetworkGeoffrey E. Hinton, Oriol Vinyals, Jay B. Dean — 2015
• Knowledge Transfer Pre-trainingZhiyuan Tang, Dong Wang, Yiqiao Pan — 2015
• Compressing LSTMs into CNNsKrzysztof J. Geras, Abdelrahman Mohamed, Rich Caruana — 2015
• Distilling Knowledge from Deep Networks with Applications to Healthcare DomainZhengping Che, Sanjay Purushotham, Robinder G. Khemani — 2015
• Discriminative segmental cascades for feature-rich phone recognitionHao Tang, Weiran Wang, Kevin Gimpel — 2015
• Distilling Model KnowledgeGeorge Papamakarios — 2015
• Transfer learning for speech and language processingDong Wang, Thomas Fang Zheng — 2015
• Blending LSTMs into CNNsKrzysztof J. Geras, Abdelrahman Mohamed, Rich Caruana — 2015
• Do Deep Convolutional Nets Really Need to be Deep (Or Even Convolutional)?Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou — 2016
• Wise teachers train better DNN acoustic modelsRyan Price, Ken-ichi Iso, Koichi Shinoda — 2016
• An investigation into using parallel data for far-field speech recognitionYanmin Qian, Tian Tan, Dong Yu — 2016
• Towards implicit complexity control using variable-depth deep neural networks for automatic speech recognitionShawn Tan, Khe Chai Sim — 2016
• Divergence estimation based on deep neural networks and its use for language identificationYosuke Kashiwagi, Congying Zhang, Daisuke Saito — 2016
• Rapid adaptation for deep neural networks through multi-task learningZhen Huang, Jinyu Li, Sabato Marco Siniscalchi — 2015
• Deep Neural Network for Automatic Speech Recognition: from the Industry's ViewJinyu Li — 2014
• Sequence Student-Teacher Training of Deep Neural NetworksJeremy H. M. Wong, Mark Gales — 2016
• Distilling Knowledge from Ensembles of Neural Networks for Speech RecognitionYevgen Chebotar, Austin Waters — 2016

Related papers

• DETERMINING QUALITY REQUIREMENTS AT THE UNIVERSITIES TO IMPROVE THE QUALITY OF EDUCATIONNor Hanim Mustafa, Dinmukhamed Kelesbayev, Zh.D. Alibekova — 2018
• Using DataGrid Control to Realize DataBase of Querying in VB6.0Shu Hu — 2000
• Study and Two Types of Typical Usage of DataGrid Web Server ControlLuo Hai-tao — 2005
• Bidirectional Sort and Choosing a Row to Update or Delete by Click Any Cell in DataGridXiao Tian-yuan — 2006
• Flexible Application of VSFlexGridGao Zhi-li — 2005
• GMQL: A graphical multimedia query languageZongda Wu, Guandong Xu, Yanchun Zhang — 2012
• Query Caching Method for Distributed Web CachingTakuya Asaka, Hiroyoshi Miwa — 1998