About Me
I am a final-year Ph.D. candidate (expected graduation: April 2026) at the Department of Systems Engineering and Engineering Management, the Chinese University of Hong Kong (CUHK), supervised by Prof. LIU Xunying and co-supervised by Prof. CHEN Xie. Before that, I finished my Master and Bachelor degrees in CUHK and SouthEast University (SEU) respectively.
My research interests focus on multimodal speech-language models, self-supervised learning for speech, and large-scale ASR.
🔥 News
- 2026.01: Released Covo-Audio Technical Report as a core contributor.
- 2025.12: 1 first-author paper accepted by ICASSP 2026.
- 2025.09: 1 first-author journal accepted by IEEE/ACM TASLP.
- 2025.06: 1 first-author paper and 4 co-authored papers accepted by INTERSPEECH 2025. GigaSpeech 2 accepted by ACL 2025.
- 2025.01: 2 conference papers have been accepted by ICASSP 2025.
- 2024.06: 2 conference papers have been accepted by INTERSPEECH 2024.
- 2023.12: 2 conference papers have been accepted by ICASSP 2024.
- 2023.05: 5 conference papers have been accepted by INTERSPEECH 2023 including 1 first-author paper.
- 2023.02: 2 conference papers have been accepted by ICASSP 2023 and 1 journal has been accepted by IEEE TASLP.
- 2022.06: 3 conference papers have been accepted by INTERSPEECH 2022 including 1 first-author paper.
- 2021.06: 1 journal has been accepted by IEEE TASLP.
📖 Educations
- Since 2021.09, Ph.D. student, The Chinese University of Hong Kong (CUHK), China.
- 2019.09 - 2020.06, Master of Computer Science, the Chinese University of Hong Kong (CUHK), China.
- 2015.06 - 2019.07, Bachelor of Software Engineering, SouthEast University (SEU), China.
💻 Experience
- 2025.12 - Now, Research Intern, Hunyuan, Tencent, Shenzhen, China.
- 2025.06 - 2025.12, Research Intern, Tencent AI Lab, Shenzhen, China.
- 2024.06 - 2025.06, Research Intern, Noah’s Ark Lab, Huawei, Hong Kong SAR, China.
- 2023.10 - 2024.02, Remote Research Intern, Speech Lab, Alibaba DAMO Academy, China.
- 2022.03 - 2023.09, Research Intern, International Digital Economy Academy (IDEA), China.
- 2020.08 - 2021.09, Research Assistant, The Chinese University of Hong Kong (CUHK), China.
📝 Selected Publications
-
Exploring SSL Discrete Tokens For Multilingual Automatic Speech Recognition
Mingyu Cui, Mengzhe Geng, Yiwen Shao, Jiawen Kang, Lingwei Meng, Dingdong Wang, Chenxing Li, Meng Yu, Xunying Liu
IEEE ICASSP 2026 -
Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR
Mingyu Cui, Yifan Yang, Jiajun Deng, Jiawen Kang, Shujie Hu, Tianzi Wang, Zhaoqing Li, Shiliang Zhang, Xie Chen, Xunying Liu
ISCA Interspeech 2025 -
Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
Mingyu Cui, Mengzhe Geng, Jiajun Deng, Chengxi Deng, Jiawen Kang, Shujie Hu, Guinan Li, Tianzi Wang, Zhaoqing Li, Xie Chen, Xunying Liu
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) -
Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems
Mingyu Cui, Jiawen Kang, Jiajun Deng, Xi Yin, Yutao Xie, Xie Chen, Xunying Liu
ISCA Interspeech 2023, Dublin, Ireland (Oral Presentation) -
Two-pass Decoding and Cross-adaptation Based System Combination of End-to-End Conformer and Hybrid TDNN ASR Systems
Mingyu Cui, Jiajun Deng, Shujie Hu, Xurong Xie, Tianzi Wang, Shoukang Hu, Mengzhe Geng, Boyang Xue, Xunying Liu, Helen Meng
ISCA Interspeech 2022, Incheon, Korea -
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement
Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, et al.
ACL 2025More paper details please find in Google Scholar
🎖 Teaching Assistance
- ENGG 1120 C, Linear Algebra
- FTEC 4006, Internet Finance
- SEEM 2420, Operations Research I