| Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach MH Lee, JH Chang ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and …, 2021 | 4 | 2021 |
| Deep Neural Network Calibration for E2E Speech Recognition System MH Lee, JH Chang Proc. Interspeech 2021, 4064-4068, 2021 | 4 | 2021 |
| Korean speech recognition based on grapheme MH Lee, JH Chang The Journal of the Acoustical Society of Korea 38 (5), 601-606, 2019 | 4 | 2019 |
| Regularizing Transformer-based Acoustic Models by Penalizing Attention Weights MH Lee, JH Chang, SE Lee, JS Seong, C Park, H Kwon Proc. Interspeech 2022, 56-60, 2022 | 3* | 2022 |
| Whisper Multilingual Downstream Task Tuning Using Task Vectors JH Kang, JH Lee, MH Lee, JH Chang Proc. Interspeech 2024, 2385-2389, 2024 | 1 | 2024 |
| Cross-Modal Learning for CTC-Based ASR: Leveraging CTC-Bertscore and Sequence-Level Training MH Lee, SE Lee, JE Choi, JH Chang 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023 | 1 | 2023 |
| Balanced-Wav2Vec: Enhancing Stability and Robustness of Representation Learning Through Sample Reweighting Techniques MH Lee, JH Lee, DH Kim, YE Ko, JH Chang Proc. Interspeech 2024, 2024 | | 2024 |
| Knowledge Distillation From Offline to Streaming Transducer: Towards Accurate and Fast Streaming Model by Matching Alignments JH Mo, JJ Jeon, MH Lee, JH Chang 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-7, 2023 | | 2023 |
Joon-Hyuk ChangHanyang University, Full Professor在 hanyang.ac.kr 的电子邮件经过验证
Joon-Hyuk ChangHanyang University, Full Professor在 hanyang.ac.kr 的电子邮件经过验证