Hung-yi Lee

Latest

• Joint Fullband-Subband Modeling for High-Resolution SingFake Detection
• MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
• Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
• DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
• HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment
• VoiceNoNG: High-Quality Speech Editing Model without Hallucinations
• Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
• Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits
• Desta: Enhancing speech language models through descriptive speech-text alignment