Learning small-size DNN with output-distribution-based criteria J Li, R Zhao, JT Huang, Y Gong Fifteenth annual conference of the international speech communication …, 2014 | 360 | 2014 |
Variable-component deep neural network for robust speech recognition J Li, R Zhao, Y Gong US Patent 10,019,990, 2018 | 227 | 2018 |
Improving RNN transducer modeling for end-to-end speech recognition J Li, R Zhao, H Hu, Y Gong 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019 | 205 | 2019 |
Large-scale domain adaptation via teacher-student learning YG J Li, ML Seltzer, X Wang, R Zhao arXiv preprint arXiv:1708.05466, 0 | 162 | |
On the comparison of popular end-to-end models for large scale speech recognition J Li, Y Wu, Y Gaur, C Wang, R Zhao, S Liu arXiv preprint arXiv:2005.14327, 2020 | 155 | 2020 |
Advancing acoustic-to-word CTC model J Li, G Ye, A Das, R Zhao, Y Gong 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 118 | 2018 |
Developing RNN-T models surpassing high-performance hybrid models with customization capability J Li, R Zhao, Z Meng, Y Liu, W Wei, S Parthasarathy, V Mazalov, Z Wang, ... arXiv preprint arXiv:2007.15188, 2020 | 114 | 2020 |
Internal language model estimation for domain-adaptive end-to-end speech recognition Z Meng, S Parthasarathy, E Sun, Y Gaur, N Kanda, L Lu, X Chen, R Zhao, ... 2021 IEEE Spoken Language Technology Workshop (SLT), 243-250, 2021 | 111 | 2021 |
Learning student DNN via output distribution J Li, R Zhao, JT Huang, Y Gong US Patent 11,429,860, 2022 | 105 | 2022 |
Towards code-switching ASR for end-to-end CTC models K Li, J Li, G Ye, R Zhao, Y Gong ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 100 | 2019 |
Advancing connectionist temporal classification with attention modeling A Das, J Li, R Zhao, Y Gong 2018 IEEE International conference on acoustics, speech and signal …, 2018 | 69 | 2018 |
Developing far-field speaker system via teacher-student learning J Li, R Zhao, Z Chen, C Liu, X Xiao, G Ye, Y Gong 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 67 | 2018 |
Acoustic-to-word model without OOV J Li, G Ye, R Zhao, J Droppo, Y Gong 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017 | 59 | 2017 |
Improved training for online end-to-end speech recognition systems S Kim, ML Seltzer, J Li, R Zhao arXiv preprint arXiv:1711.02212, 2017 | 51 | 2017 |
Exploring pre-training with alignments for rnn transducer based end-to-end speech recognition H Hu, R Zhao, J Li, L Lu, Y Gong ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 40 | 2020 |
Advancing acoustic-to-word CTC model with attention and mixed-units A Das, J Li, G Ye, R Zhao, Y Gong IEEE/ACM Transactions on Audio, Speech, and Language Processing 27 (12 …, 2019 | 34 | 2019 |
On addressing practical challenges for rnn-transducer R Zhao, J Xue, J Li, W Wei, L He, Y Gong 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2021 | 31 | 2021 |
Surgical management and outcomes of the aortic root in acute type A aortic dissection J Qiu, J Wu, E Xie, X Luo, JF Chen, W Gao, W Jiang, J Qiu, R Zhao, C Yu The Annals of Thoracic Surgery 110 (1), 136-143, 2020 | 31 | 2020 |
Transfer learning approaches for streaming end-to-end speech recognition system V Joshi, R Zhao, RR Mehta, K Kumar, J Li arXiv preprint arXiv:2008.05086, 2020 | 27 | 2020 |
Domain adaptation in speech recognition via teacher-student learning J Li, ML Seltzer, X Wang, R Zhao, Y Gong US Patent 10,885,900, 2021 | 26 | 2021 |