Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model

• URL: http://arxiv.org/abs/2511.20470v1
• Date: Tue, 25 Nov 2025 16:34:07 GMT
• Title: Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model
• Authors: Genís Plaja-Roglans, Yun-Ning Hung, Xavier Serra, Igor Pereira,
• Abstract summary: In this work, we study the potential of diffusion models to advance toward bridging this gap.<n>We focus on generative singing voice separation relying on corresponding pairs of isolated vocals and mixtures for training.<n>To align with creative mixtures, we leverage latent diffusion: the system generates samples encoded in a compact latent space, and subsequently decodes these into audio.
• Score: 12.393086516044866
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach, the source overlap and correlation in music signals poses an inherent challenge. Also, accessing all sources in the mixture is crucial to train these systems, while complicated. Attempts to address these challenges in a generative fashion exist, however, the separation performance and inference efficiency remain limited. In this work, we study the potential of diffusion models to advance toward bridging this gap, focusing on generative singing voice separation relying only on corresponding pairs of isolated vocals and mixtures for training. To align with creative workflows, we leverage latent diffusion: the system generates samples encoded in a compact latent space, and subsequently decodes these into audio. This enables efficient optimization and faster inference. Our system is trained using only open data. We outperform existing generative separation systems, and level the compared non-generative systems on a list of signal quality measures and on interference removal. We provide a noise robustness study on the latent encoder, providing insights on its potential for the task. We release a modular toolkit for further research on the topic.

Related papers

• Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models [58.946955321428845]
  This work presents self-rewarding sequential Monte Carlo (SMC)<n>Our algorithm stems from the observation that most existing MDLMs rely on a confidence-based sampling strategy.<n>We introduce the trajectory-level confidence as a self-rewarding signal for assigning particle importance weights.
  arXiv  Detail & Related papers  (2026-02-02T09:21:45Z)
• Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures [12.393086516044866]
  In this work, we explore singing voice separation from real music recordings using a diffusion model.<n>We present a study of the sampling algorithm, highlighting the effects of the user-configurable parameters.
  arXiv  Detail & Related papers  (2025-11-26T12:49:35Z)
• High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling [65.02357548201188]
  We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning.<n>Our framework operates by synthesizing the desired separated sound spectrograms directly from a noise distribution, conditioned concurrently on the mixed audio input and associated visual information.
  arXiv  Detail & Related papers  (2025-09-26T08:46:00Z)
• DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization [6.6567375919025995]
  Language-queried Audio Source Separation (LASS) enables open-vocabulary sound separation via natural language queries.<n>We introduce a training-free framework leveraging generative priors for zero-shot LASS.<n>Our approach effectively repurposes pretrained diffusion models for source separation, achieving competitive performance without task-specific supervision.
  arXiv  Detail & Related papers  (2025-06-03T13:24:57Z)
• Unleashing the Power of Natural Audio Featuring Multiple Sound Sources [54.38251699625379]
  Universal sound separation aims to extract clean audio tracks corresponding to distinct events from mixed audio.<n>We propose ClearSep, a framework that employs a data engine to decompose complex naturally mixed audio into multiple independent tracks.<n>In experiments, ClearSep achieves state-of-the-art performance across multiple sound separation tasks.
  arXiv  Detail & Related papers  (2025-04-24T17:58:21Z)
• Bass Accompaniment Generation via Latent Diffusion [0.0]
  We present a controllable system for generating single stems to accompany musical mixes of arbitrary length. At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations. Our controllable conditional audio generation framework represents a significant step forward in creating generative AI tools to assist musicians in music production.
  arXiv  Detail & Related papers  (2024-02-02T13:44:47Z)
• SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis [0.0]
  We introduce SpecDiff-GAN, a neural vocoder based on HiFi-GAN. We show the merits of our proposed model for speech and music synthesis on several datasets.
  arXiv  Detail & Related papers  (2024-01-30T09:17:57Z)
• DITTO: Diffusion Inference-Time T-Optimization for Music Generation [49.90109850026932]
  Diffusion Inference-Time T-Optimization (DITTO) is a frame-work for controlling pre-trained text-to-music diffusion models at inference-time. We demonstrate a surprisingly wide-range of applications for music generation including inpainting, outpainting, and looping as well as intensity, melody, and musical structure control.
  arXiv  Detail & Related papers  (2024-01-22T18:10:10Z)
• Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion [85.54515118077825]
  This paper proposes a linear diffusion model (LinDiff) based on an ordinary differential equation to simultaneously reach fast inference and high sample quality. To reduce computational complexity, LinDiff employs a patch-based processing approach that partitions the input signal into small patches. Our model can synthesize speech of a quality comparable to that of autoregressive models with faster synthesis speed.
  arXiv  Detail & Related papers  (2023-06-09T07:02:43Z)
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation [88.49030739715701]
  This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
  arXiv  Detail & Related papers  (2023-03-15T02:16:39Z)
• Fast accuracy estimation of deep learning based multi-class musical source separation [79.10962538141445]
  We propose a method to evaluate the separability of instruments in any dataset without training and tuning a neural network. Based on the oracle principle with an ideal ratio mask, our approach is an excellent proxy to estimate the separation performances of state-of-the-art deep learning approaches.
  arXiv  Detail & Related papers  (2020-10-19T13:05:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.