| 2025 | ICASSP | Improving Contextual ASR with Enhanced Phrase-Level Representation Based on MCTC Loss. | Ming Fang, Tao Wei, Kai Guo, Ziyang Zhuang, Yan Shi, Ning Cheng, Shaojun Wang, Jing Xiao |
| 2025 | ICASSP | Token-Level Contextual Network with Ladder-Shaped Attention for End-to-End ASR. | Ming Fang, Kai Guo, Tao Wei, Ziyang Zhuang, Yan Shi, Ning Cheng, Shaojun Wang, Jing Xiao |
| 2025 | ICASSP | EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed. | Ziyang Zhuang, Chenfeng Miao, Kun Zou, Ming Fang, Tao Wei, Zijian Li, Ning Cheng, Wei Hu, Shaojun Wang, Jing Xiao |
| 2025 | Interspeech | Towards Efficiently Whisper Fine-tuning with Monotonic Alignments. | Ziyang Zhuang, Tao Wei, Ming Fang, Ning Cheng, Shaojun Wang, Jing Xiao |
| 2024 | ICASSP | Improving Attention-Based End-to-End Speech Recognition by Monotonic Alignment Attention Matrix Reconstruction. | Ziyang Zhuang, Kun Zou, Chenfeng Miao, Ming Fang, Tao Wei, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao |
| 2024 | Interspeech | E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition. | Kun Zou, Fengyun Tan, Ziyang Zhuang, Chenfeng Miao, Tao Wei, Shaodan Zhai, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao |
| 2022 | Interspeech | Towards Efficiently Learning Monotonic Alignments for Attention-based End-to-End Speech Recognition. | Chenfeng Miao, Kun Zou, Ziyang Zhuang, Tao Wei, Jun Ma, Shaojun Wang, Jing Xiao |