@inproceedings{kuan2024can,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,}
@article{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},journal={arXiv preprint arXiv:2411.05361},year={2024},bibtex_show=true,}
Building a Taiwanese Mandarin Spoken Language Model: A First Attempt
Chih-Kai Yang , Yu-Kuan Fu , Chen-An Li , and 8 more authors
@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},journal={arXiv preprint arXiv:2411.07111},year={2024},bibtex_show=true,}
@misc{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},}
@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,}
@article{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,}
@article{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,}
@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,}
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
@article{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,}
@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,}