Ke-Han Lu

@article{lu2025desta25audio,
  title={DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment},
  author={Lu, Ke-Han and Chen, Zhehuai and Fu, Szu-Wei and Yang, Chao-Han Huck and Huang, Sung-Feng and Yang, Chih-Kai and Yu, Chee-En and Chen, Chun-Wei and Chen, Wei-Chih and Huang, Chien-yu and others},
  journal={arXiv preprint arXiv:2507.02768},
  year={2025}
}

@inproceedings{lu2025speechifeval,
  title={{Speech-IFEval}: Evaluating instruction-following and quantifying catastrophic forgetting in speech-aware language models},
  author={Lu, Ke-Han and Kuan, Chun-Yi and Lee, Hung-yi},
  booktitle={Interspeech 2025},
  year={2025}
}

@inproceedings{
  huang2025dynamicsuperb,
  title={Dynamic-{SUPERB} Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks},
  author={Chien-yu Huang and others},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025},
  url={https://openreview.net/forum?id=s7lzZpAW7T}
}

@INPROCEEDINGS{Lu2025Developing,
  author={Lu, Ke-Han and Chen, Zhehuai and Fu, Szu-Wei and Yang, Chao-Han Huck and Balam, Jagadeesh and Ginsburg, Boris and Wang, Yu-Chiang Frank and Lee, Hung-Yi},
  booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data}, 
  year={2025},
  pages={1-5},
  doi={10.1109/ICASSP49660.2025.10889444}
}

@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}
}

@inproceedings{lu24c_interspeech,
  title     = {DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment},
  author    = {Ke-Han Lu and Zhehuai Chen and Szu-Wei Fu and He Huang and Boris Ginsburg and Yu-Chiang Frank Wang and Hung-yi Lee},
  year      = {2024},
  booktitle = {Interspeech 2024},
  pages     = {4159--4163},
  doi       = {10.21437/Interspeech.2024-457}
}

@inproceedings{huang2024dynamic,
  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}
}

@inproceedings{lu2023context,
  title={A context-aware knowledge transferring strategy for CTC-based ASR},
  author={Lu, Ke-Han and Chen, Kuan-Yu},
  booktitle={2022 IEEE Spoken Language Technology Workshop (SLT)},
  pages={60--67},
  year={2023},
  organization={IEEE}
}

@article{yu2022non,
  title={Non-autoregressive asr modeling using pre-trained language models for chinese speech recognition},
  author={Yu, Fu-Hao and Chen, Kuan-Yu and Lu, Ke-Han},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={30},
  pages={1474--1482},
  year={2022},
  publisher={IEEE}
}

@article{lu2021transformer,
  title={A transformer-based cross-modal fusion model with adversarial training for VQA challenge 2021},
  author={Lu, Ke-Han and Fang, Bo-Han and Chen, Kuan-Yu},
  journal={arXiv preprint arXiv:2106.13033},
  year={2021}
}