Ke-Han Lu
I am Ke-Han Lu, a second-year Ph.D. student at National Taiwan University, working under the supervision of Prof. Hung-Yi Lee. My research interests lie in the field of Multimodal Language Models, with a particular focus on cross-modal alignment and leveraging powerful language models to enhance multi-modal systems.
Selected Publications
- Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models
- Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language ModelsInterSpeech 2025, Paper
Chi-Yuan Hsiao, Ke-Han Lu, Kai-Wei Chang, Chih-Kai Yang, Wei-Chih Chen, Hung-yi Lee, - Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
- SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning
- Building a taiwanese mandarin spoken language model: A first attempt(Co-first author) Technical Report, ArXiv preprint., Paper
Chih-Kai Yang, Yu-Kuan Fu, Chen-An Li, Yi-Cheng Lin, Yu-Xiang Lin, Wei-Chih Chen, Ho Lam Chung, Chun-Yi Kuan, Wei-Ping Huang, Ke-Han Lu*, Tzu-Quan Lin, Hsiu-Hsuan Wang, En-Pei Hu, Chan-Jan Hsu, Liang-Hsuan Tseng, I Chiu, Ulin Sanga, Xuanjun Chen, Po-chun Hsu, Shu-wen Yang, Hung-yi Lee, - DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text AlignmentInterSpeech 2024, Paper
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, He Huang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee, - HypR: A comprehensive study for ASR hypothesis revising with a reference corpus
- Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech
- Investigating zero-shot generalizability on mandarin-english code-switched asr and speech-to-text translation of recent foundation models with self-supervision and weak supervisionICASSP workshop 2024, Paper
Chih-Kai Yang, Kuan-Po Huang, Ke-Han Lu, Chun-Yi Kuan, Chi-Yuan Hsiao, Hung-yi Lee, - A Context-aware Knowledge Transferring Strategy for CTC-based ASR
- Non-autoregressive ASR Modeling using Pre-trained Language Models for Chinese Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, Paper
Fu-Hao Yu, Kuan-Yu Chen, Ke-Han Lu, - A Transformer-based Cross-modal Fusion Model with Adversarial Training for VQA Challenge 2021Poster spotlight, VQA workshop, CVPR 2021, Paper, Video, LeaderBoard
Ke-Han Lu, Bo-Han Fang, Kuan-Yu Chen, - ntust-nlp-2 at ROCLING-2021 Shared Task: BERT-based semantic analyzer with word-level informationROCLING 2021: Conference on Computational Linguistics and Speech Processing, Paper
Ke-Han Lu, Kuan-Yu Chen, - A Preliminary Study of Formosa Speech Recognition Challenge 2020 – Taiwanese ASRInternational Journal of Computational Linguistics and Chinese Language Processing, Paper
Fu-Hao Yu, Ke-Han Lu, Yi-Wei Wang, Wei-Zhe Chang, Wei-Kai Huang, Kuan-Yu Chen,
Education
- National Taiwan University
- Ph.D. in Communication Engineering
- Feb 2024 - Present
- Ph.D. in Communication Engineering
- National Taiwan University of Science and Technology
- M.S. in Computer Science and Information Engineering
- Sep 2020 - Feb 2023
- M.S. in Computer Science and Information Engineering
- National Taiwan University of Science and Technology
- B.S. in Computer Science and Information Engineering
- Sep 2016 - Jun 2020
- B.S. in Computer Science and Information Engineering
Honors
- NVIDIA Academic Grant Program
- NSTC Graduate Research Fellowship（NSTC-GRF）
- 16th TaiwanTech Outstanding Youth Award
Skills
- Programming: Python, PyTorch, Javascript, Latex
- Software and tools: Linux, Docker, Git, NeMo, Megatron-LM, ESPNET, Huggingface Transformers, fairseq
- Language: Mandarin(native), English(fluent)