Zengwei Yao

Joined

September 2023

Names

Zengwei Yao (Preferred)

Emails

****@outlook.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

Xiaomi Corporation (xiaomi.com)

2022 – 2023

MS student

Harbin Institute of Technology (hit.edu.cn)

2019 – 2022

Undergrad student

South China Normal University (scnu.edu.cn)

2015 – 2019

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation
Zengwei Yao, Wei Kang, Han Zhu, Liyong Guo, Lingxuan Ye, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Long Lin, Daniel Povey
- ICLR 2026 Poster
- Readers: Everyone
TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
Fanxu Meng, Pingzhi Tang, Zengwei Yao, Xing Sun, Muhan Zhang
- NeurIPS 2025 spotlight
- Readers: Everyone
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
Zengwei Yao, Wenjie Pei, Fanglin Chen, Guangming Lu, David Zhang
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Readers: Everyone
CR-CTC: Consistency regularization on CTC for improved speech recognition
Zengwei Yao, Wei Kang, Xiaoyu Yang, Fangjun Kuang, Liyong Guo, Han Zhu, Zengrui Jin, Zhaoqing Li, Long Lin, Daniel Povey
- ICLR 2025 Poster
- Readers: Everyone
Libriheavy: A 50, 000 Hours ASR Corpus with Punctuation Casing and Context
Wei Kang, Xiaoyu Yang, Zengwei Yao, Fangjun Kuang, Yifan Yang, Liyong Guo, Long Lin, Daniel Povey
- ICASSP 2024
- Readers: Everyone
Zipformer: A faster and better encoder for automatic speech recognition
Zengwei Yao, Liyong Guo, Xiaoyu Yang, Wei Kang, Fangjun Kuang, Yifan Yang, Zengrui Jin, Long Lin, Daniel Povey
- ICLR 2024
- Readers: Everyone
PromptASR for Contextualized ASR with Controllable Style
Xiaoyu Yang, Wei Kang, Zengwei Yao, Yifan Yang, Liyong Guo, Fangjun Kuang, Long Lin, Daniel Povey
- ICASSP 2024
- Readers: Everyone
Zipformer: A faster and better encoder for automatic speech recognition
Zengwei Yao, Liyong Guo, Xiaoyu Yang, Wei Kang, Fangjun Kuang, Yifan Yang, Zengrui Jin, Long Lin, Daniel Povey
- ICLR 2024 oral
- Readers: Everyone
Delay-penalized CTC Implemented Based on Finite State Transducer
Zengwei Yao, Wei Kang, Fangjun Kuang, Liyong Guo, Xiaoyu Yang, Yifan Yang, Long Lin, Daniel Povey
- INTERSPEECH 2023
- Readers: Everyone
Blank-regularized CTC for Frame Skipping in Neural Transducer
Yifan Yang, Xiaoyu Yang, Liyong Guo, Zengwei Yao, Wei Kang, Fangjun Kuang, Long Lin, Xie Chen, Daniel Povey
- CoRR 2023
- Readers: Everyone

View all 28 publications

Co-Authors

View all 38 co-authors