Get started
Author

Hung-yi Lee

The ICASSP 2026 Humdial Challenge: Benchmarking Human-Like Spoken Dialogue Systems in the LLM Era
2026 · Zhixian Zhao, Shuiyuan Wang, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 3
TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild
2026 · Chang, Kai-Wei, Lin, Yi-Cheng, et al. · arXiv (Cornell University) · 1
PDF
The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era
2026 · Zhao, Zhixian, Wang, Shuiyuan, et al. · arXiv (Cornell University) · 1
PDF
Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models
2026 · Liao, Pei-Jun, Lee, Hung-Shin, et al. · arXiv (Cornell University)
PDF
AudioICL-Bench: A Benchmark for Large Audio Language Model In-Context Learning
2026 · Chen, Jia-Hung, Lin, Yi-Cheng, et al. · arXiv (Cornell University)
PDF
Joint Optimization of Tool Creation and Use for Large Language Model Agents
2026 · Tam, Zhi Rui, Lin, Chieh-Yen, et al. · arXiv (Cornell University)
PDF
INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval
2026 · Li, Chen-An, Lee, Hung-yi · arXiv (Cornell University)
PDF
CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models
2026 · Chen, Chun-Wei, Lin, Tzu-Quan, et al. · arXiv (Cornell University)
PDF
Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
2026 · Chou, Wei-Chieh, Chen, Xuanjun, et al. · arXiv (Cornell University)
PDF
Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach
2026 · Wei, Tzu-Chieh, Lin, Yi-Cheng, et al. · arXiv (Cornell University)
PDF
Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech
2026 · Chen, Xuanjun, Wu, Yun-Shing, et al. · arXiv (Cornell University)
PDF
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
2026 · Lin, Yi-Cheng, Tsai, Yun-Shao, et al. · arXiv (Cornell University)
PDF
LLM-Codec: Neural Audio Codec Meets Language Model Objectives
2026 · Chung, Ho-Lam, Chen, Yiming, et al. · arXiv (Cornell University)
PDF
MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
2026 · Chen, Szu-Chi, Tsai, I-Ning, et al. · arXiv (Cornell University)
PDF
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
2026 · Lin, Yi-Cheng, Hirota, Yusuke, et al. · arXiv (Cornell University)
PDF
TiCo: Time-Controllable Spoken Dialogue Model
2026 · Chang, Kai-Wei, Chen, Wei-Chih, et al. · arXiv (Cornell University)
PDF
The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS
2026 · Chen, Kuan-Yu, Lin, Yi-Cheng, et al. · arXiv (Cornell University)
PDF
TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
2026 · Tseng, Liang-Hsuan, Lee, Hung-yi · arXiv (Cornell University)
PDF
On Calibration of Large Language Models: From Response To Capability
2026 · Yang, Sin-Han, Wu, Cheng-Kuang, et al. · arXiv (Cornell University)
PDF
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
2026 · Hsu, Chan-Jan, Tseng, Liang-Hsuan, et al. · arXiv (Cornell University)
PDF
AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
2026 · Tzu-Han Lin, Wei-Lin Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions
2026 · Chan-Jan Hsu, Jaeyeon Kim, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models
2025 · Lin, Yu-Xiang, Chiang, Cheng-Han, et al. · arXiv (Cornell University)
PDF
Works count: 23
Citation count: 5
H-index: 1
I10-index:
Year
Topic
Type