Publications

* indicates equal contribution.

Reproducible Research & Reliable Evaluation

• SURE-Tagger: Structured Speech Representations for Compositional Evaluation and Targeted Data Selection
  Jing Peng, Huifei Wang, Weihan Chen, Shuo Gao, Bicheng Zhang, Junhao Du, Hanqi Li, Chaolei Liu, Wen Wen, Tao Liu, Xu Li, Yu Xi, Shuai Wang, Kai Yu
  arXiv preprint, 2026

  Semi-structured speech representations for compositional evaluation and targeted data selection.

  arXiv · Code · Project
• SURE-EVAL: A Systematic and Unified Agentic Framework for Reproducible Evaluation
  Jing Peng*, Junhao Du*, Yixuan Wang*, Bowen Wang*, Hanqi Li*, Chaolei Liu, Weihan Chen, Haohui Xie, Ruichen Sun, Chenghao Wang, Wen Wen, Guanyu Chen, Xiaoyu Gu, Haoyu Li, Yiwei Guo, Bohan Li, Tao Liu, Yucheng Wang, Yu Xi, Yihua Zhou, Qiang Zhou, Feng Lu, Shuai Wang, Kai Yu
  NCMMSC 2026 (accepted, Oral), 2026
  arXiv · Code · Project
• A Unified and Reproducible Experimentation Framework for Speech Understanding
  Jing Peng*, J. Du*, C. Wang*, H. Li*, Y. Yang*, Y. Wang, X. Gu, G. Chen, Y. Wang, J. Li, Z. Zhao, H. Wang, W. Tu, H. Li, D. Ma, L. Qian, Y. Xi, W. Wen, J. Guo, H. Zhang, S. Fan, W. Jiang, S. Wang, K. Yu
  Interspeech 2026 (accepted, Oral), 2026
  arXiv · Project
• ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models
  B. Li, W. Huang, Y. Qiu, Y. Guo, H. Wang, Z. Li, Jing Peng, Z. Ma, X. Chen, K. Yu
  ICASSP 2026 (accepted, Oral), 2026
  arXiv

Cross-Modal Speech Alignment

• In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models
  Yiwei Guo, Siqi Huang, Bohan Li, Jing Peng, Hankun Wang, Zhihan Li, Kai Yu
  arXiv preprint, 2026
  arXiv
• TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
  Jing Peng*, C. Wang*, Y. Yang, L. Qian, J. Li, Y. Xi, S. Wang, K. Yu
  Interspeech 2026 (accepted, Oral), 2026
  arXiv · Project
• TASU: Text-Only Alignment for Speech Understanding
  Jing Peng, Y. Yang, X. Li, Y. Xi, Q. Tang, Y. Fang, J. Li, K. Yu
  ICASSP 2026 (accepted, Oral), 2026
  arXiv · Project
• Multilingual TASU
  NCMMSC 2026 (accepted, Oral; Spotlight Candidate), 2026
• dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
  Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Yiwei Guo, Colin Zhang, Shuai Wang, Kai Yu
  arXiv preprint, 2026
  arXiv
• Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
  Y. Fang*, Jing Peng*, X. Li, Y. Xi, C. Zhang, G. Zhong, K. Yu
  ASRU 2025 (accepted), 2025
  arXiv

Surveys

• A Survey on Speech Large Language Models for Understanding
  Jing Peng*, Yucheng Wang*, Bohan Li, Yiwei Guo, Hankun Wang, Yangui Fang, Yu Xi, Haoyu Li, Xu Li, Ke Zhang, Shuai Wang, Kai Yu
  IEEE Journal of Selected Topics in Signal Processing, 2025
  arXiv · DOI · Project

Automatic Speech Recognition

• TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
  Qingshun She*, Jing Peng*, Yangui Fang, Yu Xi, Kai Yu
  Findings of EMNLP 2026 (accepted), 2026
  arXiv
• RAS: a Reliability Oriented Metric for Automatic Speech Recognition
  W. Huang, Y. Qiu, B. Li, Y. Guo, Jing Peng, H. Wang, X. Chen, K. Yu
  Interspeech 2026 (accepted, Oral), 2026
  arXiv
• SCORE
  NCMMSC 2026 (accepted, Poster), 2026
• Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
  Y. Fang, B. Cheng, Jing Peng, X. Li, Y. Xi, C. Zhang, G. Zhong
  ASRU 2025 (accepted), 2025
  arXiv

ASR in Complex Scenarios

• ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization
  Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li, Kunyang Peng, Feng Xue, Shuai Wang, Kai Yu
  arXiv preprint, 2026

  A multilingual benchmark for evaluation-side transcript canonicalization, covering 181 phenomenon types across 12 languages, with the SENA metric and TACS agent skill for normalization.

  arXiv
• VISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASR
  Xiaoyu Gu, Yu Xi, Chencheng Wang, Zonghan Zhou, Haoyu Li, Jing Peng, Kai Yu
  arXiv preprint, 2026
  arXiv
• Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization
  Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li, Kunyang Peng, Feng Xue, Lu Chen, Shuai Wang, Kai Yu
  NCMMSC 2026 (accepted, Poster), 2026
  arXiv
• G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition
  Jing Peng*, Z. Chen*, H. Li*, Y. Wang, D. Ma, M. Li, Y. Du, D. Xu, K. Yu, S. Wang
  Findings of EMNLP 2026 (accepted), 2026
  arXiv
• MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
  Junjie Li, Jing Peng, Yangui Fang, Shuai Wang, Kai Yu
  ICASSP 2026 (accepted, Poster), 2026
  arXiv
• MoE EEND
  NCMMSC 2026 (accepted, Oral), 2026
• PA-TSE
  NCMMSC 2026 (accepted, Oral), 2026
• Joint Decoding Method for Controllable Contextual Speech Recognition Based on Speech LLM
  Y. Fang*, J. Peng*, Y. Xi, X. Li, H. Li, C. Zhang, G. Zhong, K. Yu
  arXiv preprint, 2025
  arXiv

Agentic Systems for Language & Research

• XFlow: An Executable Protocol Programming System for Reliable Multi-Agent Workflows
  H. Li*, Jing Peng*, Z. Wang, L. Chen, K. Yu
  arXiv preprint, 2026
  arXiv
• Making AI Scientists Auditable from Evidence to Claim
  Zijian Wang, Hanqi Li, Ziyue Yang, Zijian Hu, Shenghan Zuo, Yunzhe Zhang, Da Ma, Danyu Luo, Chenrun Wang, Jing Peng, Tiancheng Huang, Sijia Guo, Huayang Wang, Zichen Zhu, Senyu Han, Yilu Cao, Bo Chen, Xin Chen, Kai Yu, Lu Chen
  arXiv preprint, 2026
  arXiv

Voice & Audio Agents

• Audio-Mind: An Auditable Agentic Framework for Audio Understanding
  Yucheng Wang*, Jing Peng*, Hanqi Li, Chenghao Wang, Wenming Tu, Yu Xi, Zhaokai Sun, Kai Yu, Shuai Wang
  submitted to EMNLP 2026, 2026
  arXiv
• VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track
  W. Tu, J. Gao, Y. Huo, Y. Wang, Jing Peng, B. Li, Z. Ma, T. Liu, S. Fan, K. Yu, X. Chen, Z. Zheng
  Interspeech 2026 (accepted, Oral), 2026
  arXiv

Spatial Audio

• DiS-TSE
  NCMMSC 2026 (accepted, Poster), 2026