[Paper Note] USE: A Unified Model for Universal Sound Separation and Extraction

Related Papers

• [ICML 2026] A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation
• [ACL 2026] UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
• [ICML 2026] Attend to Anything: Foundation Model for Unified Human Attention Modeling
• [ICLR 2026] AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching
• [AAAI 2026] Cross-Space Synergy: A Unified Framework for Multimodal Emotion Recognition in Conversation