KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition D Yu, K Yao, H Su, G Li, F Seide 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 516 | 2013 |
Adaptation of context-dependent deep neural networks for automatic speech recognition K Yao, D Yu, F Seide, H Su, L Deng, Y Gong 2012 IEEE Spoken Language Technology Workshop (SLT), 366-369, 2012 | 255 | 2012 |
Error back propagation for sequence training of context-dependent deep networks for conversational speech transcription H Su, G Li, D Yu, F Seide 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 179 | 2013 |
Conservatively adapting a deep neural network in a recognition system D Yu, K Yao, H Su, G Li, F Seide US Patent 9,177,550, 2015 | 95 | 2015 |
Experiments on parallel training of deep neural network using model averaging H Su, H Chen arXiv preprint arXiv:1507.01239, 2015 | 79 | 2015 |
Alignment restricted streaming recurrent neural network transducer J Mahadeokar, Y Shangguan, D Le, G Keren, H Su, T Le, CF Yeh, ... 2021 IEEE Spoken Language Technology Workshop (SLT), 52-59, 2021 | 66 | 2021 |
Multi-softmax deep neural network for semi-supervised training H Su12, H Xu Multi-softmax Deep Neural Network for Semi-supervised Training, 2015 | 27 | 2015 |
Dissecting user-perceived latency of on-device E2E speech recognition Y Shangguan, R Prabhavalkar, H Su, J Mahadeokar, Y Shi, J Zhou, C Wu, ... arXiv preprint arXiv:2104.02207, 2021 | 24 | 2021 |
Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions. H Xu, H Su, C Ni, X Xiao, H Huang, ES Chng, H Li INTERSPEECH, 1315-1319, 2016 | 20 | 2016 |
Semi-supervised training for bottle-neck feature based DNN-HMM hybrid systems. H Xu, H Su, CE Siong, H Li INTERSPEECH, 2078-2082, 2014 | 16 | 2014 |
Detecting institutional dialog acts in police traffic stops V Prabhakaran, C Griffiths, H Su, P Verma, N Morgan, JL Eberhardt, ... Transactions of the Association for Computational Linguistics 6, 467-481, 2018 | 13 | 2018 |
Improvements on transducing syllable lattice to word lattice for keyword search H Su, Y He, J Hieronymus 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 12 | 2015 |
Factor Analysis Based Speaker Verification Using ASR. H Su, S Wegmann Interspeech, 2223-2227, 2016 | 8 | 2016 |
Syllable based keyword search: Transducing syllable lattices to word lattices H Su, J Hieronymus, Y He, E Fosler-Lussier, S Wegmann 2014 IEEE Spoken Language Technology Workshop (SLT), 489-494, 2014 | 8 | 2014 |
Combining speech and speaker recognition: A joint modeling approach H Su University of California, Berkeley, 2018 | 7 | 2018 |
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization L Tang, I Shalyminov, AW Wong, J Burnsky, JW Vincent, Y Yang, S Singh, ... arXiv preprint arXiv:2402.13249, 2024 | 3 | 2024 |
Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios. J Mahadeokar, Y Shi, Y Shangguan, C Wu, A Xiao, H Su, D Le, O Kalinli, ... Interspeech, 2107-2111, 2021 | 3 | 2021 |
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets H Aboutalebi, H Song, Y Xie, A Gupta, J Sun, H Su, I Shalyminov, ... arXiv preprint arXiv:2403.03194, 2024 | 1 | 2024 |
Dynamic speech endpoint detection with regression targets D Liang, H Su, T Singh, J Mahadeokar, S Puri, J Zhu, E Thomaz, ... ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 1 | 2023 |
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders Y Zhang, S Singh, S Sengupta, I Shalyminov, H Su, H Song, S Mansour arXiv preprint arXiv:2403.04314, 2024 | | 2024 |