AURA: Unified Multimodal Framework for Conversational Music Editing
AURA, a unified multimodal framework for conversational music editing, uses a multimodal large language model to interpret the complete dialogue history, an optional image, and reference audio, distilling the editing intent into compact concept tokens, enabling precise edits while preserving unaffected content.
Quoc-Huy Trinh, Minh-Van Nguyen, Debesh Jha
· 0 citations