About Me

Hi! Here is Wenxi Chen (陈文熙). I am an undergraduate student at Shanghai Jiao Tong University (SJTU), majoring in computer science. Since 2023, I have been working as a research intern at the X-Lance Lab at SJTU, under the supervision of Prof. Xie Chen.

I’m generally interested in understanding & generation in speech and audio, as well as multimodal large language models. My previous projects have involved audio self-supervised learning, audio scene classification, audio captioning and end-to-end spoken dialogue models.

Selected Publications

For the most up-to-date information, please visit my Google Scholar profile.
(* indicates equal contribution)

SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
_{Keqi Deng, Wenxi Chen, Xie Chen, Phil Woodland}
_{ACL 2025}
_paper

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
_{Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen}
_{ACL 2025 (Findings)}
_{paper / demo / code}

SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs
_{Wenxi Chen*, Ziyang Ma*, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Kai Yu, Xie Chen}
_{ICASSP 2025}
_{paper / code}

DRCap: Decoding CLAP Latents with Retrieval-augmented Generation for Zero-shot Audio Captioning
_{Xiquan Li, Wenxi Chen, Ziyang Ma, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Qiuqiang Kong, Xie Chen}
_{ICASSP 2025 (oral)}
_{paper / code}

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
_{Wenxi Chen, Yuzhe Liang, Ziyang Ma, Zhisheng Zheng, Xie Chen}
_{IJCAI 2024}
_{paper / code}

Activities

Experience

Research Intern @ Microsoft Research Asia (MSRA)
General Artificial Intelligence Group, Beijing, China
_{2024.09-CURRENT}

Competition

IEEE ICME 2024 Challenge Semi-supervised Acoustic Scene Classification under Domain Shift
_{Ranked 2nd, Team Leader}

DCASE Challenge 2024 Task 6: Automated Audio Captioning
_{Ranked 3rd, Team Leader}

Awards

Rongchang Science and Technology Innovation Scholarship, 2024

CV

Here is my CV (Chinese).

Contact

Email: 1029713857@sjtu.edu.cn