# Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models Source: [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:54:27.044Z Authors: Tornike Karchkhadze, Mohammad Rasool Izadi, Shlomo Dubnov Published: 2024-09-18T22:35:26.000Z ## Abstract Diffusion models have recently shown strong potential in both music generation and music source separation tasks. Although in early stages, a trend is emerging towards integrating these tasks into a single framework, as both involve generating musically aligned parts and can be seen as facets of the same generative process. In this work, we introduce a latent diffusion-based multi-track generation model capable of both source separation and multi-track music synthesis by learning the joint probability distribution of tracks sharing a musical context. Our model also enables arrangement generation by creating any subset of tracks given the others. We trained our model on the Slakh2100 dataset, compared it with an existing simultaneous generation and separation model, and observed significant improvements across objective metrics for source separation, music, and arrangement generation tasks. Sound examples are available at https://msg-ld.github.io/. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-track music generation on Slakh2100 (test)](): Multi-track music generation; Slakh2100 (test); FAD: 1.31. - [Inner Track Rhythmic Stability on Slakh2100](): Inner Track Rhythmic Stability; Slakh2100; IRS (Bass): 0.041. - [Multi-track Music Generation (Drum Subjective Evaluation) on Slakh2100 (test)](): Multi-track Music Generation (Drum Subjective Evaluation); Slakh2100 (test); Subjective Score (Group 1): 1.2. - [Multi-track Rhythmic Synchronization on Slakh2100](): Multi-track Rhythmic Synchronization; Slakh2100; CBS: 0.3861. - [Multi-track Music Generation (Mixture Subjective Evaluation) on Slakh2100 (test)](): Multi-track Music Generation (Mixture Subjective Evaluation); Slakh2100 (test); Subjective Score (Group 1): 1.5. - [Multi-track Music Generation on MUSDB18](): Multi-track music generation; MUSDB18; CBS: 0.386. - [Multi-track Music Generation on Slakh2100](): Multi-track music generation; Slakh2100; CBS: 0.386. ## Original sources and implementation [Original paper]() [PDF]()