To see the world, to face the danger, to break the limits.

Name: Han Yin (Han) | 尹涵

Occupation: PhD Candidate

Research Interests: Audio Understanding, Multimodal Large Language Models

Hobbies: Singing, Traveling, Basketball

E-mail: hanyin@kaist.ac.kr; yinh72906@gmail.com; yinhan@mail.nwpu.edu.cn

😊 Hello! My name is Han Yin, you can call me Han. I'm interested in Audio Understanding, Processing and Multimodal Large Language Models. Feel free to email me for any questions!

📑 First Author of: EnvSDD (the first curated large-scale environmental sound deepfake detection benchmark); TQ-SED (the first SED system with LASS front-end).

📖 Reviewer of: ICME, ICASSP, TASLP, Computer Science Review

📳 Github; Google Scholar; Linked In; Chinese Version of This Page

Education Experience

School of Electrical Engineering @ Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea, 09/2025 ~ now

– PhD Candidate (KAIST Full Scholarship), Audio Understanding. Advisor: Prof. Jung-woo Choi

School of Marine Science and Technology @ Northwestern Polytechnical University (NWPU), China, 09/2018 ~ 07/2022

– Bachelor of Engineering, Detection, Guidence and Control Technology. Advisor: Prof. Yintao Wang

– GPA: 3.622/4.0 (Top 2 in Class)

School of Marine Science and Technology @ Northwestern Polytechnical University (NWPU), China, 09/2022 ~ 03/2025

– Master of Engineering, Information Technology. Advisor: Prof. Jianfeng Chen

– GPA: 91/100 (Top 1 in Class)

Events

• 2025-09-01 🍾 I will study at Smart Sound Lab, KAIST with Prof. Choi as an International PhD student with KAIST Full Scholarship!
• 2025-07-09 🌇 End working as an algorithm engineer in Speech Group, Tongyi Lab, Alibaba, Hangzhou, China.
• 2025-05-19 👏 Two papers (EnvSDD: Benchmarking Environmental Sound Deepfake Detection), (Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization) were accepted by Interspeech, 2025!
• 2025-04-09 🍾 Begin working as an algorithm engineer in Speech Group, Tongyi Lab, Alibaba, Hangzhou, China.
• 2025-03-30 🎓 Graduated from NWPU, got my Master Degree of Engineering, thx to everyone along this wonderful journey!
• 2025-01-11 👏 The paper (Passive homing method with reinforcement learning for a single hydrophone) was published on ACTA ACUSTICA!
• 2025-01-06 👏 The paper (Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection) was accepted by ICASSP Workshop, 2025!
• 2024-12-21 👏 The paper (Exploring Text-Queried Sound Event Detection with Audio Source Separation) was accepted by ICASSP, 2025!
• 2024-09-30 🌇 End my internship in Speech Group, Tongyi Lab, Alibaba, Hangzhou, China.
• 2024-09-02 👏 The paper (Multi-granularity acoustic information fusion for sound event detection) was accepted by Signal Processing, Elseiver (JCR Q2)!
• 2024-08-14 🎉 Got the 2nd place in Alibaba Intern AI Challenge, win a PS5!
• 2024-06-30 🌇 End my internship in Fortemedia Singapore Pte. Ltd, Singapore.
• 2024-06-30 🎉 Our team got the 1st place on objective single model track in IEEE DCASE Challenge 2024 Task9 (Language-Queried Audio Source Separation) - [Tech Report]!
• 2024-06-20 🍾 Begin my internship in Speech Group, Tongyi Lab, Alibaba, Hangzhou, China (Mentor: Siqi Zheng&Chong Deng&Hui Wang)!
• 2024-06-14 🌇 End my internship in JLESS Lab, Lianfeng Acoustic Technologies Co., Ltd., , China.
• 2024-04-01 🍾 Begin my internship in Fortemedia Singapore Pte. Ltd, Singapore (Remote, Mentor: Yang Xiao, Leader: Rohan Kumar Das)!
• 2024-03-13 👏 The paper (Audiolog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning) was accepted by ICME 2024, IEEE!
• 2024-02-05 👨‍💻 The IEEE ICME grand challenge we are organizing is officially launched (Semi-supervised Acoustic Scene Classification under Domain Shift) - [Paper]!
• 2023-12-19 🎉 Our team got the 4tn place in ICASSP 2024 Cadenza Challenge, and the paper (Sub-Band and Full-Band Interactive U-Net with Dprnn for Demixing Cross-Talk Stereo Music) was accepted by ICASSPW 2024! I did an oral presentation in Seoul, Korea.
• 2023-10-02 👏 The paper (Convolutional Recurrent Neural Network with Attention for 3D Speech Enhancement) was accepted by ICSPCC 2023, IEEE! I did an oral presentation in ZhengZhou, China.
• 2023-05-31 🎉 Our team got the 1st place on track B in IEEE DCASE Challenge 2023 Task4 (Sound Event Detection with Soft Labels) - [Tech Report]!
• 2023-02-20 🎉 Our team got the 2nd place in ICASSP 2023 L3DAS Challenge, and the paper (3D Audio Signal Processing Systems for Speech Enhancement and Sound Localization and Detection) was accepted by ICASSP 2023!
• 2022-11-22 🎉 Our team got the 1st place in iFLYTEK A.I. 2022 Challenge!
• 2022-06-15 🍾 Begin my internship in JLESS Lab, Lianfeng Acoustic Technologies Co., Ltd., China (Mentor: Jisheng Bai)!

Honors & Awards

• Guorui Scholarship, Northwestern Polytechnical University (about Top 3%), 2022-2023.
• First-class Scholarship, Northwestern Polytechnical University (about Top 14.7%), 2018-2019 and 2022-2023.