| Recent advances in deep learning for speech research at Microsoft L Deng, J Li, JT Huang, K Yao, D Yu, F Seide, M Seltzer, G Zweig, X He, ... Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International …, 2013 | 734 | 2013 |
| Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers JT Huang, J Li, D Yu, L Deng, Y Gong 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 562 | 2013 |
| An overview of noise-robust automatic speech recognition J Li, L Deng, Y Gong, R Haeb-Umbach IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (4), 745-777, 2014 | 460 | 2014 |
| Restructuring of deep neural network acoustic models with singular value decomposition. J Xue, J Li, Y Gong INTERSPEECH, 2365-2369, 2013 | 370 | 2013 |
| Learning small-size DNN with output-distribution-based criteria. J Li, R Zhao, JT Huang, Y Gong INTERSPEECH, 1910-1914, 2014 | 247 | 2014 |
| Feature learning in deep neural networks-studies on speech recognition tasks D Yu, ML Seltzer, J Li, JT Huang, F Seide arXiv preprint arXiv:1301.3605, 2013 | 246 | 2013 |
| Singular Value Decomposition Based Low-footprint Speaker Adaptation and Personalization for Deep Neural Network J Xue, J Li, D Yu, M Seltzer, Y Gong ICASSP, 2014 | 168 | 2014 |
| End-to-End attention based text-dependent speaker verification SX Zhang, Z Chen, Y Zhao, J Li, Y Gong Spoken Language Technology Workshop (SLT), 2016 IEEE, 171-178, 2016 | 163 | 2016 |
| Robust Automatic Speech Recognition: A Bridge to Practical Applications J Li, L Deng, R Haeb-Umbach, Y Gong Academic Press, 2015 | 141 | 2015 |
| High-performance HMM adaptation with joint compensation of additive and convolutive distortions via vector Taylor series J Li, L Deng, D Yu, Y Gong, A Acero 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), 65-70, 2007 | 139 | 2007 |
| Restructuring deep neural network acoustic models J Xue, E Stoimenov, J Li, Y Gong US Patent 9,728,184, 2017 | 116 | 2017 |
| Restructuring deep neural network acoustic models J Xue, E Stoimenov, J Li, Y Gong US Patent 9,728,184, 2017 | 116 | 2017 |
| Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM J Li, D Yu, JT Huang, Y Gong Spoken Language Technology Workshop (SLT), 2012 IEEE, 131-136, 2012 | 113 | 2012 |
| Shared hidden layer combination for speech recognition systems J Li, J Xue, Y Gong US Patent 9,520,127, 2016 | 111 | 2016 |
| Shared hidden layer combination for speech recognition systems J Li, J Xue, Y Gong US Patent 9,520,127, 2016 | 111 | 2016 |
| A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions J Li, L Deng, D Yu, Y Gong, A Acero Computer Speech & Language 23 (3), 389-405, 2009 | 111 | 2009 |
| Recent progresses in deep learning based acoustic models D Yu, J Li IEEE/CAA Journal of Automatica Sinica 4 (3), 396-409, 2017 | 108 | 2017 |
| An analysis of convolutional neural networks for speech recognition JT Huang, J Li, Y Gong 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 95 | 2015 |
| Large-scale domain adaptation via teacher-student learning J Li, ML Seltzer, X Wang, R Zhao, Y Gong arXiv preprint arXiv:1708.05466, 2017 | 93 | 2017 |
| Variable-component deep neural network for robust speech recognition J Li, R Zhao, Y Gong US Patent 10,019,990, 2018 | 92 | 2018 |
Yifan GongPrincipal Science Manager, Microsoft Corp.Verifierad e-postadress på microsoft.com
