Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition Paper • 2510.08047 • Published Oct 9 • 7
Awesome papers from 臺大李宏毅 (Hung-yi Lee) Collection Recent papers authored by Hung-yi Lee. Sorted by ID • 8 items • Updated Oct 24 • 17
WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection Paper • 2510.05305 • Published Oct 6 • 1
TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics Paper • 2509.26329 • Published Sep 30 • 2
ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality Paper • 2505.15773 • Published May 21 • 1
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment Paper • 2507.02768 • Published Jul 3 • 18
Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems Paper • 2509.13989 • Published Sep 17 • 3