Szu-Wei Fu

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

You Are What You Train: Rethinking Training Data Quality, Targets, and Architectures for Universal Speech Enhancement

Reinforcement Learning Enhanced Full-Duplex Spoken Dialogue Language Models for Conversational Interactions

Segment, Associate, and Classify: Decoupled Audio-Visual Segmentation Framework

VoiceNoNG: High-Quality Speech Editing Model without Hallucinations