Follow
Hang Su
Hang Su
Tech Lead Manager at Amazon Inc.
Verified email at amazon.com - Homepage
Title
Cited by
Cited by
Year
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
5152013
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
2552012
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
1792013
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
952015
Experiments on parallel training of deep neural network using model averaging
H Su, H Chen
arXiv preprint arXiv:1507.01239, 2015
792015
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
642021
Multi-softmax deep neural network for semi-supervised training
H Su12, H Xu
Multi-softmax Deep Neural Network for Semi-supervised Training, 2015
272015
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
242021
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
202016
Semi-supervised training for bottle-neck feature based DNN-HMM hybrid systems
H Xu, H Su, ES Chng, H Li
Fifteenth annual conference of the international speech communication …, 2014
152014
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
122018
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
122015
Factor Analysis Based Speaker Verification Using ASR.
H Su, S Wegmann
Interspeech, 2223-2227, 2016
82016
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
82014
Combining speech and speaker recognition: A joint modeling approach
H Su
University of California, Berkeley, 2018
72018
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
32021
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
12024
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
12023
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
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
J He, H Su, J Cai, I Shalyminov, H Song, S Mansour
arXiv preprint arXiv:2403.04073, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–20