Publications

2026

1. In Progress

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

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

   arXiv preprint arXiv:2601.14728, 2026

   Bib PDF

   @article{kuan2026aqascore,
     title = {AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering},
     author = {Kuan, Chun-Yi and Chang, Kai-Wei and Lee, Hung-yi},
     journal = {arXiv preprint arXiv:2601.14728},
     year = {2026},
     bibtex_show = true,
   }

2. ICASSP 2026

   AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering

   Chun-Yi Kuan , and Hung-yi Lee

   In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2026

   arXiv Bib PDF

   @inproceedings{kuan2024can,
     title = {AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering},
     author = {Kuan, Chun-Yi and Lee, Hung-yi},
     booktitle = {ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     year = {2026},
     organization = {IEEE},
     bibtex_show = true,
   }

2025

1. TASLP

   From Alignment to Advancement: Bootstrapping Audio-Language Alignment With Synthetic Data

   Chun-Yi Kuan , and Hung-yi Lee

   In IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2025

   arXiv Bib PDF

   @inproceedings{Kuan2025FromAlignment,
     author = {Kuan, Chun-Yi and Lee, Hung-yi},
     title = {From Alignment to Advancement: Bootstrapping Audio-Language Alignment With Synthetic Data},
     booktitle = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
     year = {2025},
     volume = {33},
     pages = {4604--4619},
     doi = {10.1109/TASLPRO.2025.3626233},
     organization = {IEEE},
     bibtex_show = true,
   }

2. INTERSPEECH

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

   Chun-Yi Kuan , and Hung-yi Lee

   In 2025 Conference of the International Speech Communication Association (INTERSPEECH) , 2025

   arXiv Bib PDF

   @inproceedings{kuan2025teaching,
     title = {Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples},
     author = {Kuan, Chun-Yi and Lee, Hung-yi},
     booktitle = {2025 Conference of the International Speech Communication Association (INTERSPEECH)},
     year = {2025},
     organization = {ISCA},
     bibtex_show = true,
   }

3. NAACL 2025

   Gender Bias in Instruction-Guided Speech Synthesis Models

   Chun-Yi Kuan , and Hung-yi Lee

   In 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics , 2025

   arXiv Bib PDF

   @inproceedings{kuan2025genderbiasinstructionguidedspeech,
     title = {Gender Bias in Instruction-Guided Speech Synthesis Models},
     author = {Kuan, Chun-Yi and Lee, Hung-yi},
     year = {2025},
     primaryclass = {cs.CL},
     bibtex_show = true,
     booktitle = {2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics}
   }

4. ICASSP 2025

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

   Chun-Yi Kuan , and Hung-yi Lee

   In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2025

   arXiv Bib PDF

   @inproceedings{kuan2024cao,
     title = {Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning},
     author = {Kuan, Chun-Yi and Lee, Hung-yi},
     booktitle = {ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     year = {2025},
     organization = {IEEE},
     bibtex_show = true,
   }

2024

1. ICLR 2025

   Dynamic-superb phase-2: A collaboratively expanding benchmark for measuring the capabilities of spoken language models with 180 tasks

   Chien-yu Huang , Wei-Chih Chen , Shu-wen Yang , and 8 more authors

   In The Thirteenth International Conference on Learning Representations (ICLR 2025) , 2024

   arXiv Bib PDF

   @inproceedings{huang2024dynamic,
     title = {Dynamic-superb phase-2: A collaboratively expanding benchmark for measuring the capabilities of spoken language models with 180 tasks},
     author = {Huang, Chien-yu and Chen, Wei-Chih and Yang, Shu-wen and Liu, Andy T and Li, Chen-An and Lin, Yu-Xiang and Tseng, Wei-Cheng and Diwan, Anuj and Shih, Yi-Jen and Shi, Jiatong and others},
     year = {2024},
     bibtex_show = true,
     booktitle = {The Thirteenth International Conference on Learning Representations (ICLR 2025)}
   }

2. BRO 2024 SUM

   Building a Taiwanese Mandarin Spoken Language Model: A First Attempt

   Chih-Kai Yang , Yu-Kuan Fu , Chen-An Li , and 8 more authors

   2024

   arXiv Bib PDF

   @article{yang2024building,
     title = {Building a Taiwanese Mandarin Spoken Language Model: A First Attempt},
     author = {Yang, Chih-Kai and Fu, Yu-Kuan and Li, Chen-An and Lin, Yi-Cheng and Lin, Yu-Xiang and Chen, Wei-Chih and Chung, Ho Lam and Kuan, Chun-Yi and Huang, Wei-Ping and Lu, Ke-Han and others},
     year = {2024},
     bibtex_show = true,
     booktitle = {The Summer Intensive Research Camp on Universal Speech-to-Speech Models (SIRC-US2S 2024)}
   }

3. SLT 2024

   Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation

   Chun-Yi Kuan , Chih-Kai Yang , Wei-Ping Huang , and 2 more authors

   In IEEE Spoken Language Technology Workshop 2024 (SLT) , 2024

   arXiv Bib PDF

   @inproceedings{kuan2024speechcopilotleveraginglargelanguage,
     title = {Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation},
     author = {Kuan, Chun-Yi and Yang, Chih-Kai and Huang, Wei-Ping and Lu, Ke-Han and Lee, Hung-yi},
     year = {2024},
     booktitle = {IEEE Spoken Language Technology Workshop 2024 (SLT)},
     url = {https://arxiv.org/abs/2407.09886},
     bibtex_show = true,
     organization = {IEEE},
   }

4. EMNLP 2024

   Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course

   Cheng-Han Chiang , Wei-Chih Chen , Chun-Yi Kuan , and 2 more authors

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , Nov 2024

   arXiv Bib PDF

   @inproceedings{chiang-etal-2024-large,
     title = {Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course},
     author = {Chiang, Cheng-Han and Chen, Wei-Chih and Kuan, Chun-Yi and Yang, Chienchou and Lee, Hung-yi},
     booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
     month = nov,
     year = {2024},
     address = {Miami, Florida, USA},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.emnlp-main.146},
     doi = {10.18653/v1/2024.emnlp-main.146},
     pages = {2489--2513},
     bibtex_show = true,
   }

5. SLT 2024

   Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models

   Yi-Cheng Lin , Tzu-Quan Lin , Chih-Kai Yang , and 4 more authors

   In IEEE Spoken Language Technology Workshop 2024 (SLT) , Nov 2024

   arXiv Bib PDF

   @inproceedings{lin2024listen,
     title = {Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models},
     author = {Lin, Yi-Cheng and Lin, Tzu-Quan and Yang, Chih-Kai and Lu, Ke-Han and Chen, Wei-Chih and Kuan, Chun-Yi and Lee, Hung-yi},
     booktitle = {IEEE Spoken Language Technology Workshop 2024 (SLT)},
     year = {2024},
     organization = {IEEE},
     bibtex_show = true,
   }

6. INTERSPEECH

   Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models

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

   In 2024 Conference of the International Speech Communication Association (INTERSPEECH) , Nov 2024

   arXiv Bib PDF

   @inproceedings{kuan2024understanding,
     title = {Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models},
     author = {Kuan, Chun-Yi and Huang, Wei-Ping and Lee, Hung-yi},
     booktitle = {2024 Conference of the International Speech Communication Association (INTERSPEECH)},
     pages = {1--6},
     year = {2024},
     organization = {ISCA},
     bibtex_show = true,
   }

7. ICASSP 2024

   Dynamic-superb: Towards a dynamic, collaborative, and comprehensive instruction-tuning benchmark for speech

   Chien-yu Huang , Ke-Han Lu , Shih-Heng Wang , and 8 more authors

   In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Nov 2024

   arXiv Bib PDF

   @inproceedings{huang2024dynamid,
     title = {Dynamic-superb: Towards a dynamic, collaborative, and comprehensive instruction-tuning benchmark for speech},
     author = {Huang, Chien-yu and Lu, Ke-Han and Wang, Shih-Heng and Hsiao, Chi-Yuan and Kuan, Chun-Yi and Wu, Haibin and Arora, Siddhant and Chang, Kai-Wei and Shi, Jiatong and Peng, Yifan and others},
     booktitle = {ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {12136--12140},
     year = {2024},
     organization = {IEEE},
     bibtex_show = true,
   }

2023

1. ICASSP 2024

   Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision

   Chih-Kai Yang , Kuan-Po Huang , Ke-Han Lu , and 3 more authors

   In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Nov 2023

   arXiv Bib PDF

   @inproceedings{yang2023investigating,
     title = {Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision},
     author = {Yang, Chih-Kai and Huang, Kuan-Po and Lu, Ke-Han and Kuan, Chun-Yi and Hsiao, Chi-Yuan and Lee, Hung-yi},
     booktitle = {ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     year = {2023},
     organization = {IEEE},
     bibtex_show = true,
   }

2. ASRU 2023

   Towards General-Purpose Text-Instruction-Guided Voice Conversion

   Chun-Yi Kuan , Chen-An Li , Tsu-Yuan Hsu , and 5 more authors

   In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) , Nov 2023

   arXiv Bib PDF

   @inproceedings{kuan2023towards,
     title = {Towards General-Purpose Text-Instruction-Guided Voice Conversion},
     author = {Kuan, Chun-Yi and Li, Chen-An and Hsu, Tsu-Yuan and Lin, Tse-Yang and Chung, Ho-Lam and Chang, Kai-Wei and Chang, Shuo-Yiin and Lee, Hung-yi},
     booktitle = {2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
     pages = {1--8},
     year = {2023},
     organization = {IEEE},
     bibtex_show = true,
   }