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 Get in touch
Portrait of Kuan-Yu Chen (Daniel)
01

About

I am a Ph.D. student and AI researcher working at the intersection of generative audio and trustworthy AI — building systems that edit and synthesize speech under real-world noise, and studying how such systems can be protected, attacked, or biased.

My greatest trait is a passion for learning. I approach every opportunity eager to absorb new skills and knowledge, and I treat challenges as chances to grow beyond my comfort zone. I see failures not as setbacks but as stepping stones: each one offers a lesson that refines my approach and lets me adapt with resilience and determination.

02

Research Interests

Speech Editing & Synthesis

Noise-resilient, zero-shot speech editing with in-context enhancement for insertion and replacement in real-world acoustic conditions.

Audio Security & Watermarking

Watermark-as-trigger backdoors, data-to-model ownership protection, and robustness against acoustic filtering and model pruning.

Fairness in Instruction TTS

Compositional analysis of gender bias across social status, career, and persona cues, uncovering multi-dimensional interaction effects.

Music Information Retrieval

Query-by-humming, instrument analysis, and diffusion-based guitar tone morphing in latent audio spaces.

03

Publications

Full list on Google Scholar
  1. 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
  2. 2026ISCAS 2026

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

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

    Scholar
  3. 2026arXiv 2026

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

    Yi-Cheng Lin, Yu-Sheng Tsai*, Kuan-Yu Chen*, Hsuan-Yu Huang*, Huang-Cheng Chou*, Hung-yi Lee

    arXiv Scholar

    * Equal contribution

  4. 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
  5. 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
  6. 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
  7. 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
  8. 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

  9. 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
  10. 2025ICEIC 2025

    Chromagram Features Analysis for Learning-Based Query by Humming Systems

    Kuan-Yu Chen, Jian-Jiun Ding

    Scholar
  11. 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. Jan 2026 – Present

    Ph.D., Communications Engineering (Data Science & Smart Networking)

    National Taiwan University

    Advisors: Yu Tsao and Jian-Jiun Ding.

  2. Sep 2024 – Dec 2025

    M.S. Track, Communications Engineering (Data Science & Smart Networking)

    National Taiwan University

    Transferred directly to the Ph.D. program. Advisor: Jian-Jiun Ding.

  3. Sep 2019 – Jun 2024

    B.S., Biomechatronics Engineering

    National Taiwan University

Experience

  1. Sep 2024 – Present

    AI Researcher Intern

    Inventec Corporation · AI Research Center

    Research mentor: Jeng-Lin Li.

  2. Jul 2024 – Aug 2024

    Audio Engineer

    Inventec Corporation

  3. 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.