MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
We present MGE-LDM, a unified latent diffusion framework for simultaneous music generation, source imputation, and query-driven source separation. Unlike prior approaches constrained to fixed instrument classes, MGE-LDM learns a joint distribution over full mixtures, submixtures, and individual stems within a single compact latent diffusion model. At inference, MGE-LDM enables (1) complete mixture generation, (2) partial generation (i.e., source imputation), and (3) text-conditioned extraction of arbitrary sources. By formulating both separation and imputation as conditional inpainting tasks in the latent space, our approach supports flexible, class-agnostic manipulation of arbitrary instrument sources. Notably, MGE-LDM can be trained jointly across heterogeneous multi-track datasets (e.g., Slakh2100, MUSDB18, MoisesDB) without relying on predefined instrument categories. Audio samples are available at our project page: https://yoongi43.github.io/MGELDM_Samples/.
Code (0)
등록된 구현이 없습니다.
Tasks
ImputationMusic GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-Source Music Generation with Latent Diffusion
Most music generation models directly generate a single music mixture. To allow for more flexible and controllable generation, the Multi-Source Diffusion Model (MSDM) has been proposed to model music as a mixture of mult…
FADMusic GenerationEfficient Neural Music Generation
Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, s…
DenoisingMusic GenerationText-to-Music GenerationCustomized Condition Controllable Generation for Video Soundtrack
Recent advances in latent diffusion models (LDMs) have enabled data-driven paradigms for video soundtrack generation, improving multimodal alignment capabilities. However, current two-stage frameworks--which separate…
Audio SynthesisDITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation
Controllable music generation methods are critical for human-centered AI-based music creation, but are currently limited by speed, quality, and control design trade-offs. Diffusion Inference-Time T-optimization (DITTO), …
Music GenerationMotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation
Generating long-term, coherent, and realistic music-conditioned dance sequences remains a challenging task in human motion synthesis. Existing approaches exhibit critical limitations: motion graph methods rely on fixed t…
Contrastive LearningMotion SynthesisRAGRetrieval+2