GASS: Generalizing Audio Source Separation with Large-scale Data

• URL: http://arxiv.org/abs/2310.00140v1
• Date: Fri, 29 Sep 2023 21:02:07 GMT
• Title: GASS: Generalizing Audio Source Separation with Large-scale Data
• Authors: Jordi Pons, Xiaoyu Liu, Santiago Pascual, Joan Serr\`a
• Abstract summary: Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Here, we study a single general audio source separation model trained to separate speech, music, and sound events in a supervised fashion with a large-scale dataset.
• Score: 17.176462322552098
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Yet, the potential of universal source separation is limited because most existing works focus on mixes with predominantly sound events, and small training datasets also limit its potential for supervised learning. Here, we study a single general audio source separation (GASS) model trained to separate speech, music, and sound events in a supervised fashion with a large-scale dataset. We assess GASS models on a diverse set of tasks. Our strong in-distribution results show the feasibility of GASS models, and the competitive out-of-distribution performance in sound event and speech separation shows its generalization abilities. Yet, it is challenging for GASS models to generalize for separating out-of-distribution cinematic and music content. We also fine-tune GASS models on each dataset and consistently outperform the ones without pre-training. All fine-tuned models (except the music separation one) obtain state-of-the-art results in their respective benchmarks.

Related papers

• SAM Audio: Segment Anything in Audio [55.50609519820557]
  General audio source separation is a key capability for multimodal AI systems.<n>We present SAM Audio, a foundation model for general audio separation.<n>It unifies text, visual, and temporal span prompting within a single framework.
  arXiv  Detail & Related papers  (2025-12-19T22:14:23Z)
• 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)
• USAD: Universal Speech and Audio Representation via Distillation [56.91647396619358]
  Universal Speech and Audio Distillation (USAD) is a unified approach to audio representation learning.<n>USAD integrates diverse audio types - speech, sound, and music - into a single model.
  arXiv  Detail & Related papers  (2025-06-23T17:02:00Z)
• ZeroSep: Separate Anything in Audio with Zero Training [42.19808124670159]
  Audio source separation is fundamental for machines to understand complex acoustic environments.<n>Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data.<n>We investigate whether pre-trained text-guided audio diffusion models can overcome these limitations.<n>We make a surprising discovery: zero-shot source separation can be achieved purely through a pre-trained text-guided audio diffusion model.
  arXiv  Detail & Related papers  (2025-05-29T16:31:45Z)
• 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. We propose ClearSep, a framework that employs a data engine to decompose complex naturally mixed audio into multiple independent tracks. In experiments, ClearSep achieves state-of-the-art performance across multiple sound separation tasks.
  arXiv  Detail & Related papers  (2025-04-24T17:58:21Z)
• Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes [16.530816405275715]
  We present a unified model capable of simultaneously grounding both spoken language and non-speech sounds within a visual scene. Existing approaches are typically limited to handling either speech or non-speech sounds independently, or at best, together but sequentially without mixing.
  arXiv  Detail & Related papers  (2025-03-24T16:56:04Z)
• Separate This, and All of these Things Around It: Music Source Separation via Hyperellipsoidal Queries [53.30852012059025]
  Music source separation is an audio-to-audio retrieval task.<n>Recent work in music source separation has begun to challenge the fixed-stem paradigm.<n>We propose the use of hyperellipsoidal regions as queries to allow for an intuitive yet easily parametrizable approach to specifying both the target (location) and its spread.
  arXiv  Detail & Related papers  (2025-01-27T16:13:50Z)
• Universal Sound Separation with Self-Supervised Audio Masked Autoencoder [35.560261097213846]
  We propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system. The proposed methods successfully enhance the separation performance of a state-of-the-art ResUNet-based USS model.
  arXiv  Detail & Related papers  (2024-07-16T14:11:44Z)
• Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations [16.269123889392343]
  This work proposes Audio Mamba, a selective state space model for learning general-purpose audio representations. Empirical results on ten diverse audio recognition downstream tasks show that the proposed models consistently outperform comparable self-supervised audio spectrogram transformer baselines.
  arXiv  Detail & Related papers  (2024-06-04T10:19:14Z)
• Towards a Generalist and Blind RGB-X Tracker [91.36268768952755]
  We develop a single model tracker that can remain blind to any modality X during inference time. Our training process is extremely simple, integrating multi-label classification loss with a routing function. Our generalist and blind tracker can achieve competitive performance compared to well-established modal-specific models.
  arXiv  Detail & Related papers  (2024-05-28T03:00:58Z)
• Separate Anything You Describe [55.0784713558149]
  Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA) AudioSep is a foundation model for open-domain audio source separation with natural language queries.
  arXiv  Detail & Related papers  (2023-08-09T16:09:44Z)
• High-Quality Visually-Guided Sound Separation from Diverse Categories [56.92841782969847]
  DAVIS is a Diffusion-based Audio-VIsual Separation framework. It synthesizes separated sounds directly from Gaussian noise, conditioned on both the audio mixture and the visual information. We compare DAVIS to existing state-of-the-art discriminative audio-visual separation methods on the AVE and MUSIC datasets.
  arXiv  Detail & Related papers  (2023-07-31T19:41:49Z)
• Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser [34.19935635508947]
  We investigate the under-explored unaligned setting, where the goal is to recognize audio and visual events in a video with only weak labels observed. To enhance learning in this challenging setting, we incorporate large-scale contrastively pre-trained models as the modality teachers. A simple, effective, and generic method, termed Visual-Audio Label Elaboration (VALOR), is innovated to harvest modality labels for the training events.
  arXiv  Detail & Related papers  (2023-05-27T02:57:39Z)
• SLICER: Learning universal audio representations using low-resource self-supervised pre-training [53.06337011259031]
  We present a new Self-Supervised Learning approach to pre-train encoders on unlabeled audio data. Our primary aim is to learn audio representations that can generalize across a large variety of speech and non-speech tasks.
  arXiv  Detail & Related papers  (2022-11-02T23:45:33Z)
• Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data [26.058278155958668]
  We propose a three-component pipeline to train a universal audio source separator from a large, but weakly-labeled dataset: AudioSet. Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training. The proposed audio separator can be used in a zero-shot setting, learning to separate types of audio sources that were never seen in training.
  arXiv  Detail & Related papers  (2021-12-15T05:13:43Z)
• Visual Scene Graphs for Audio Source Separation [65.47212419514761]
  State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. We propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and segments this graph into subgraphs. Our pipeline is trained end-to-end via a self-supervised task consisting of separating audio sources using the visual graph from artificially mixed sounds.
  arXiv  Detail & Related papers  (2021-09-24T13:40:51Z)
• Attention Bottlenecks for Multimodal Fusion [90.75885715478054]
  Machine perception models are typically modality-specific and optimised for unimodal benchmarks. We introduce a novel transformer based architecture that uses fusion' for modality fusion at multiple layers. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks.
  arXiv  Detail & Related papers  (2021-06-30T22:44:12Z)

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.