Chun-Yi Kuan

"Silence, I discover, is something you can actually hear." — Kafka on the Shore

Hello! I am a Ph.D. student at the National Taiwan University (NTU), where I am a member of the Speech Processing and Machine Learning (SPML) Lab advised by Prof. Hung-yi Lee. My research focuses on building trustworthy audio-aware large language models, with an emphasis on hallucination, abstention, and robust audio-language alignment. I am also interested in controllable audio generation, including instruction-guided text-to-audio and text-to-speech systems.

Chun-Yi Kuan

News

  • 2026.06 I made a little book game — Guess My Bookshelf.
  • 2026.06 Excited to share that our paper, Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models, has been accepted as a long paper at INTERSPEECH 2026 🇦🇺. See you in Sydney, Australia! 🐨
Show older news (1)
  • 2025.05 Our paper Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples was accepted to Interspeech 2025 🇳🇱.

Selected Publications

  1. Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models

    Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qingming Tang, Ankur Gandhe, Hung-yi Lee, Chieh-Chi Kao, Chao Wang

    Interspeech 2026

    TL;DRUses fine-grained feedback from audio-aware LLMs to make text-to-audio models follow instructions more faithfully.

  2. AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering

    Chun-Yi Kuan, Kai-Wei Chang, Hung-yi Lee

    arXiv preprint · 2026

    TL;DRScores text-to-audio alignment from an audio-aware LLM's confidence in answering 'Yes' to targeted questions, catching fine-grained mismatches that similarity metrics like CLAPScore miss.

  3. Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models

    Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee

    arXiv preprint · 2026

    TL;DRThe systematic study of uncertainty estimation for audio-aware LLMs, finding that semantic and verification-based methods win on general reasoning but their advantage breaks down on hallucination and unanswerable-question benchmarks.

  4. From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data

    Chun-Yi Kuan, Hung-yi Lee

    IEEE TASLP · 2025

    TL;DRBootstraps audio–language alignment with synthetic data to push audio-aware LLMs from basic alignment toward stronger reasoning.

  5. Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples

    Chun-Yi Kuan, Hung-yi Lee

    Interspeech 2025

    TL;DRCurbs hallucinations in audio-aware LLMs by teaching them what is NOT in the audio using synthesized negative samples.

  6. Gender Bias in Instruction-Guided Speech Synthesis Models

    Chun-Yi Kuan, Hung-yi Lee

    NAACL 2025

    TL;DRAudits and quantifies gender bias in instruction-guided speech synthesis models.

  7. Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning

    Chun-Yi Kuan, Hung-yi Lee

    ICASSP 2025

    TL;DRProbes whether audio-LLMs truly 'hear' via multi-task assessment and stepwise audio reasoning to reduce hallucinations.

  8. Towards General-Purpose Text-Instruction-Guided Voice Conversion

    Chun-Yi Kuan, Chen-An Li, Tsu-Yuan Hsu, Tse-Yang Lin, Ho-Lam Chung, Kai-Wei Chang, Shuo-Yiin Chang, Hung-yi Lee

    ASRU 2023

    TL;DRA first step toward general-purpose voice conversion controlled by free-form text instructions.

All publications →

Footprints

ASRU 2023 · Taipei 🇹🇼 Interspeech 2024 · Kos Island 🇬🇷 SLT 2024 · Macau 🇲🇴 ICASSP 2025 · Hyderabad 🇮🇳 Interspeech 2025 · Rotterdam 🇳🇱 ICASSP 2026 · Barcelona 🇪🇸 Interspeech 2026 · Sydney 🇦🇺 · upcoming

Conferences I attended in person · a fading paw is where I’m headed next.