I am Mohan Shi, a second-year Ph.D. student in Electrical and Computer Engineering at University of California, Los Angeles (UCLA), advised by Prof. Abeer Alwan. I received my master degree at the University of Science and Technology of China (USTC) and worked under the guidance of Prof. Li-Rong Dai for three years. My research interests span a variety of domains in the world of speech processing:

• Automatic Speech Recognition
• Speech-centric Large Language Models
• Child/Low-resource Speech Processing
• Speech Tokenization
• Cocktail Party Problems

My summer intern paper at Microsoft is now on arXiv! We use Phi-4-Multimodal for joint ASR and speaker diarization, achieving SOTA on both short and long audio.

Experience

Microsoft Research, Redmond, USA

• Research Intern, CoreAI Speech Team, June 2025 – Sep 2025
• Manager: Jinyu Li
• Mentor(s): Xiong Xiao, Ruchao Fan, Shaoshi Ling

Tencent AI Lab, Bellevue, USA (remote)

• Research Intern, Seattle Speech Lab, Sep 2023 – August 2024
• Manager: Dong Yu
• Mentor(s): Yong Xu, Shi-Xiong (Austin) Zhang

Alibaba Group, Hangzhou, China

• Research Intern, Tongyi Speech Team, Jul 2022 – May 2023
• Manager: Zhijie Yan
• Mentor(s): Shiliang Zhang, Zhihao Du

Selected Publications

1. Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio, ICASSP 2026 [pdf]
   Mohan Shi, Xiong Xiao, Ruchao Fan, Shaoshi Ling, Jinyu Li

2. STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs, ICASSP 2026 [pdf] [code]
   Kaiyuan Zhang*, Mohan Shi*, Eray Eren, Natarajan Balaji Shankar, Zilai Wang, Abeer Alwan

1. Advancing Multi-talker ASR Performance with Large Language Models, SLT 2024 [pdf]
   Mohan Shi, Zengrui Jin, Yaoxun Xu, Yong Xu, Shi-Xiong Zhang, Kun Wei, Yiwen Shao, Chunlei Zhang, Dong Yu

2. LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization, Interspeech 2024 (Oral) [pdf]
   Zengrui Jin*, Yifan Yang*, Mohan Shi*, Wei Kang, Xiaoyu Yang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Lingwei Meng, Long Lin, Yong Xu, Shi-Xiong Zhang, Daniel Povey

3. CASA-ASR: Context-Aware Speaker-Attributed ASR, Interspeech 2023 [pdf]
   Mohan Shi, Zhihao Du, Qian Chen, Fan Yu, Yangze Li, Shiliang Zhang, Jie Zhang, Li-Rong Dai

4. Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction, Interspeech 2023 (Oral) [pdf]
   Mohan Shi, Yuchun Shu, Lingyun Zuo, Qian Chen, Shiliang Zhang, Jie Zhang, Li-Rong Dai

Education

University of California, Los Angeles

• Ph.D. student, Electrical and Computer Engineering, Sep 2024 – Present
• Advisor: Abeer Alwan (Distinguished Prof., Fellow of IEEE/ISCA/ASA)

University of Science and Technology of China

• Master of Engineering, Electronic Engineering and Information Science, Sep 2021 – Jun 2024
• Advisor: Li-Rong Dai

Dalian University of Technology

• Bachelor of Engineering, Electronic Information Engineering, Sep 2017 – Jun 2021
• GPA Rank: 1 / 185