Speech · Audio · Machine Learning

Kuan-Yu Chen (Daniel)

Ph.D. Student & AI Researcher

I work on speech and audio intelligence at National Taiwan University (GICE) and the AI Research Center, Inventec — spanning zero-shot speech editing, audio-watermark security, bias in instruction TTS, and music information retrieval. I am part of the DISP Lab (NTU GICE) and the Bio-ASP Lab (Academia Sinica).

View publications Download CV Get in touch
Portrait of Kuan-Yu Chen (Daniel)
01

About

I am a direct Ph.D. student at National Taiwan University working at the intersection of generative audio and trustworthy AI. My research develops speech systems that remain useful under real-world acoustic conditions and examines how they can be protected, attacked, or biased.

I conduct research with the Bio-ASP Lab at Academia Sinica and the AI Research Center at Inventec, collaborating on robust speech generation, fairness in speech AI, and audio security.

02

Research Interests

Speech & Audio

Robust speech editing and expressive synthesis, alongside music retrieval and diffusion-based guitar tone morphing.

Security & Watermarking

Deep watermarking for audio and ECG signals, with a focus on reliable recovery, signal integrity, and watermark-based backdoors.

Fairness in Speech AI

Measuring bias in speech technologies and calibrating gender bias in instruction-guided TTS without model retraining.

Multimodal & Agents

Robust video highlight detection with missing modalities, and studies of creativity and pedagogical knowledge in LLM-based agents.

03

Publications

Full list on Google Scholar
  1. 2026arXiv 2026

    ECGWmark: Deep Watermarking of Electrocardiogram Signals With Error-Correcting Codes

    Kuan-Yu Chen, Kuan-Chen Wang, Yu Tsao, Jian-Jiun Ding

    arXiv
  2. 2026arXiv 2026

    Training-Free Instruction TTS Gender Bias Calibration Using Model-Adaptive Steering

    Kuan-Yu Chen, Yi-Cheng Lin, Jeng-Lin Li, Jian-Jiun Ding

    arXiv Code
  3. 2026arXiv 2026

    TSMD: Temporal-Stream Modality Dropout for Robust Video Highlight Detection

    Bo-Yuan Cheng*, Kuan-Yu Chen*, Po-Han Huang, Jeng-Lin Li, Jian-Jiun Ding

    arXiv Code Demo

    * Equal contribution

  4. 2026arXiv 2026

    Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI Agents

    Yi-Cheng Lin, Yu-Kai Guo, Szu-Chi Chen, Bo-Han Feng, Yun-Man Hsu, Hsiang Hsieh, Yu-Jung Lin, Yue-Ling Wu, Jia-Kai Dong, An-Yu Cheng, Yu-Han Huang, Lok-Lam Ieong, Kuan-Yu Chen, Ming-Douo Tchouang, Shao-Hua Sun, Che Lin, Jian-Jiun Ding, Hung-yi Lee

    arXiv
  5. 2026Interspeech 2026

    Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach

    Tzu-Chieh Wei, Yi-Cheng Lin, Huang-Cheng Chou, Kuan-Yu Chen, Hsin-Yen Sung, Shrikanth Narayanan, Hung-yi Lee

    arXiv Scholar
  6. 2026ISCAS 2026

    Improved Query by Humming Using Conformer-based Network with Harmonic-Aware Mechanism

    Yu-Hsuan Kung, Kuan-Yu Chen, Jian-Jiun Ding

    Scholar
  7. 2026TMLR 2026

    Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI

    Yi-Cheng Lin, Yun-Shao Tsai*, Kuan-Yu Chen*, Hsiao-Ying Huang*, Huang-Cheng Chou*, Shrikanth Narayanan, Yu Tsao, Jian-Jiun Ding, Hung-yi Lee

    arXiv Resources Collection Scholar

    * Equal contribution

  8. 2026Interspeech 2026

    The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS

    Kuan-Yu Chen, Yi-Cheng Lin, Po-Chung Hsieh, Huang-Cheng Chou, Chih-Fan Hsu, Jeng-Lin Li, Hung-yi Lee, Jian-Jiun Ding

    arXiv Code Scholar
  9. 2025APSIPA ASC 2025

    Guitar Tone Morphing by Diffusion-based Model

    Kuan-Yu Chen, Kuan-Lin Chen, Yu-Chieh Yu, Jian-Jiun Ding

    arXiv Code Demo Scholar
  10. 2025ICASSP 2026

    Bloodroot: When Watermarking Turns Poisonous for Stealthy Backdoor

    Kuan-Yu Chen, Yi-Cheng Lin, Jeng-Lin Li, Jian-Jiun Ding

    arXiv Code Scholar
  11. 2025ICASSP 2026

    Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-to-Speech Systems

    Yi-Cheng Lin, Huang-Cheng Chou, Tzu-Chieh Wei, Kuan-Yu Chen, Hung-yi Lee

    arXiv Project Hugging Face Scholar
  12. 2025EMNLP 2025

    Creativity in LLM-based Multi-Agent Systems: A Survey

    Yi-Cheng Lin*, Kang-Chieh Chen*, Zhe-Yan Li*, Tzu-Heng Wu*, Tzu-Hsuan Wu*, Kuan-Yu Chen*, Hung-yi Lee, Yun-Nung Chen

    arXiv Code Scholar

    * Equal contribution

  13. 2025EUSIPCO 2026

    SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement

    Kuan-Yu Chen, Jeng-Lin Li, De-Yan Lu, Jian-Jiun Ding

    arXiv Code Demo Scholar
  14. 2025ICEIC 2025

    Chromagram Features Analysis for Learning-Based Query by Humming Systems

    Kuan-Yu Chen, Jian-Jiun Ding

    Scholar
  15. 2024ICGSP 2024

    Mixed Music Instrument Classification Based on Instantaneous Frequency Analysis and Time-Variant Spectrum Information

    Kuan-Yu Chen, Jian-Jiun Ding, Yuan-Kai Lee

    Scholar
04

Experience & Education

Education

  1. Sep 2024 – Expected Jun 2029

    Ph.D., Communications Engineering (Direct Ph.D. Program)

    National Taiwan University

    Advisors: Yu Tsao and Jian-Jiun Ding.

  2. Sep 2019 – Jun 2024

    B.S., Biomechatronics Engineering

    National Taiwan University

Experience

  1. Feb 2026 – Present

    Ph.D. Student

    Bio-ASP Lab, Academia Sinica

    Research on ECG watermarking for biomedical signals, alongside collaborative work in speech and audio AI.

  2. Sep 2024 – Present

    AI Researcher Intern

    Inventec Corporation · AI Research Center

    Research mentor: Jeng-Lin Li.

  3. Jul 2024 – Aug 2024

    Audio Engineer

    Inventec Corporation

  4. Jan 2024 – Jun 2024

    AI Engineer Intern

    Leaderg

05

Contact

I’m always glad to discuss speech and audio research, collaborations, or new ideas — reach out through any channel below.