| An experimental analysis on integrating multi-stream spectro-temporal, cepstral and pitch information for mandarin speech recognition YB Wang, SW Li, L Lee IEEE transactions on audio, speech, and language processing 21 (10), 2006-2014, 2013 | 11 | 2013 |
| Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation PH Chi, PH Chung, TH Wu, CC Hsieh, SW Li, H Lee SLT 2021, 2020 | 171 | 2020 |
| Automated segmentation of MOOC lectures towards customized learning X Zhang, C Li, SW Li, V Zue 2016 IEEE 16th International Conference on Advanced Learning Technologies …, 2016 | 18 | 2016 |
| Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM S Sukhbaatar, O Golovneva, V Sharma, H Xu, XV Lin, B Rozière, J Kahn, ... arXiv preprint arXiv:2403.07816, 2024 | | 2024 |
| Chameleon: Mixed-modal early-fusion foundation models C Team arXiv preprint arXiv:2405.09818, 2024 | 7 | 2024 |
| Confidence calibration for natural-language understanding models that provides optimal interpretability SWD Li, M Puvvadi, TA Morse, RS Jenke, Y Zhang, RKS Pokkunuri US Patent 11,341,339, 2022 | 1 | 2022 |
| Cooperative self-training of machine reading comprehension H Luo, SW Li, M Gao, S Yu, J Glass arXiv preprint arXiv:2103.07449, 2021 | 10 | 2021 |
| Data-driven interaction techniques for improving navigation of educational videos J Kim, PJ Guo, CJ Cai, SW Li, KZ Gajos, RC Miller Proceedings of the 27th annual ACM symposium on User interface software and …, 2014 | 219* | 2014 |
| Demystifying clip data H Xu, S Xie, XE Tan, PY Huang, R Howes, V Sharma, SW Li, G Ghosh, ... arXiv preprint arXiv:2309.16671, 2023 | 58 | 2023 |
| DiffCSE: Difference-based contrastive learning for sentence embeddings YS Chuang, R Dangovski, H Luo, Y Zhang, S Chang, M Soljačić, SW Li, ... arXiv preprint arXiv:2204.10298, 2022 | 175 | 2022 |
| Dinov2: Learning robust visual features without supervision M Oquab, T Darcet, T Moutakanni, H Vo, M Szafraniec, V Khalidov, ... arXiv preprint arXiv:2304.07193, 2023 | 1275* | 2023 |
| Disentangled Training with Adversarial Examples for Robust Small-Footprint Keyword Spotting Z Wang, L Wan, B Zhang, Y Huang, SW Li, M Sun, X Lei, Z Yang ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | | 2023 |
| DUAL: Discrete spoken unit adaptive learning for textless spoken question answering GT Lin, YS Chuang, HL Chung, S Yang, HJ Chen, S Dong, SW Li, ... arXiv preprint arXiv:2203.04911, 2022 | 20* | 2022 |
| Expand, rerank, and retrieve: Query reranking for open-domain question answering YS Chuang, W Fang, SW Li, W Yih, J Glass arXiv preprint arXiv:2305.17080, 2023 | 6 | 2023 |
| Exploring efficient-tuning methods in self-supervised speech models ZC Chen, CL Fu, CY Liu, SWD Li, H Lee 2022 IEEE spoken language technology workshop (SLT), 1120-1127, 2023 | 29 | 2023 |
| Flap: Fast language-audio pre-training CF Yeh, PY Huang, V Sharma, SW Li, G Gosh 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023 | 4 | 2023 |
| Grounded and Structured Self-Supervised Pre-training of Speech for Spoken Language Model M Collaborator, SWD Li, B PI, GK Anumanchipalli, CJ Cho | | |
| Improved phoneme recognition by integrating evidence from spectro-temporal and cepstral features. S Li, L Sun, L Lee INTERSPEECH, 1177-1180, 2010 | 4 | 2010 |
| Improved tonal language speech recognition by integrating spectro-temporal evidence and pitch information with properly chosen tonal acoustic units S Li, Y Wang, L Sun, L Lee Twelfth Annual Conference of the International Speech Communication Association, 2011 | 9 | 2011 |
| Improving Learning Experience in MOOCs with Educational Content Linking SW Li Massachusetts Institute of Technology, 2017 | | 2017 |
Hung-yi LeeNational Taiwan UniversityVerified email at ntu.edu.tw
