I am Mohan Shi, a third-year Ph.D. student in Electrical and Computer Engineering at University of California, Los Angeles (UCLA). I received my master degree at the University of Science and Technology of China (USTC). 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
• Cocktail Party Problems

I am seeking research internship opportunities in 2027. Please reach out if you have any leads.

Experience

Microsoft Research, Redmond, USA

• Research Intern, CoreAI Speech Team, Jun 2026 – Sep 2026
• With Jinyu Li, Ruchao Fan, Keqi Deng, Sunit Sivasankaran
• Topic: Native encoder-free Speech-LLMs pretraining

Microsoft Research, Redmond, USA

• Research Intern, CoreAI Speech Team, Jun 2025 – Sep 2025
• With Jinyu Li, Xiong Xiao, Ruchao Fan, Shaoshi Ling
• Topic: In-context learning and emergent capabilities of Speech-LLMs; joint ASR and speaker diarization

Tencent AI Lab, Bellevue, USA (remote)

• Research Intern, Seattle Speech Lab, Sep 2023 – Aug 2024
• With Yong Xu, Shi-Xiong (Austin) Zhang, Dong Yu
• Topic: Speech-LLMs; multi-talker ASR

Alibaba Group, Hangzhou, China

• Research Intern, Speech Team (now the Qwen-Audio team), Jul 2022 – May 2023
• With Shiliang Zhang, Zhihao Du
• Topic: ASR; voice activity detection

Selected Publications

1. Teaching LLMs to Hear Who Spoke What: Metadata-Supervised Pretraining for Encoder-Free Speech-LLMs, Preprint [link]
   Mohan Shi, Ruchao Fan, Sunit Sivasankaran, Keqi Deng, Jinyu Li

2. Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs, SLT 2026 [link]
   Mohan Shi, Zilai Wang, Natarajan Balaji Shankar, Kaiyuan Zhang, Eray Eren, Abeer Alwan

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

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

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

6. LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization, Interspeech 2024 (Oral) [link]
   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

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

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

Education

University of California, Los Angeles

• Ph.D. student, Electrical and Computer Engineering, Sep 2024 – Present

University of Science and Technology of China

• Master of Engineering, Electronic Engineering and Information Science, Sep 2021 – Jun 2024

Dalian University of Technology

• Bachelor of Engineering, Electronic Information Engineering, Sep 2017 – Jun 2021