Audio Source Separation

44 papers with code • 2 benchmarks • 14 datasets

Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).

Source: Model selection for deep audio source separation via clustering analysis

A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation

karnwatcharasupat/bandit 5 Sep 2023

Cinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture.

39
05 Sep 2023

Separate Anything You Describe

audio-agi/audiosep 9 Aug 2023

In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries.

1,409
09 Aug 2023

Deep Audio Waveform Prior

Arnontu/DeepAudioWaveformPrior 21 Jul 2022

A network with relevant deep priors is likely to generate a cleaner version of the signal before converging on the corrupted signal.

8
21 Jul 2022

Separate What You Describe: Language-Queried Audio Source Separation

liuxubo717/lass 28 Mar 2022

In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e. g., "a man tells a joke followed by people laughing").

123
28 Mar 2022

Unsupervised Music Source Separation Using Differentiable Parametric Source Models

schufo/umss 24 Jan 2022

Integrating domain knowledge in the form of source models into a data-driven method leads to high data efficiency: the proposed approach achieves good separation quality even when trained on less than three minutes of audio.

54
24 Jan 2022

Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data

RetroCirce/Zero_Shot_Audio_Source_Separation 15 Dec 2021

Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training.

156
15 Dec 2021

Hybrid Neural Networks for On-device Directional Hearing

wanganran/HybridBeam AAAI 2022

On-device directional hearing requires audio source separation from a given direction while achieving stringent human-imperceptible latency requirements.

11
11 Dec 2021

Transfer Learning with Jukebox for Music Source Separation

wzaielamri/unmix 28 Nov 2021

In this work, we demonstrate how a publicly available, pre-trained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel.

34
28 Nov 2021

Unsupervised Source Separation By Steering Pretrained Music Models

ethman/tagbox 25 Oct 2021

We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining.

40
25 Oct 2021

The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

merlresearch/cocktail-fork-separation 19 Oct 2021

The cocktail party problem aims at isolating any source of interest within a complex acoustic scene, and has long inspired audio source separation research.

64
19 Oct 2021