# Bootstrapping single-channel source separation via unsupervised spatial clustering on stereo mixtures

arXiv: https://arxiv.org/abs/1811.02130 · HTML: https://mlsanity.com/paper/1811.02130/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2018.

## Built on by (most cited first, 7 of 7)

- [AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation](https://mlsanity.com/paper/2207.10141/) (2022)
- [Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data](https://mlsanity.com/paper/2105.04727/) (2021)
- [ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior](https://mlsanity.com/paper/2505.05657/) (2025)
- [Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention](https://mlsanity.com/paper/2106.09669/) (2021)
- [Learning to Separate Voices by Spatial Regions](https://mlsanity.com/paper/2207.04203/) (2022)
- [UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures](https://mlsanity.com/paper/2305.20054/) (2023)
- [Reverberation as Supervision for Speech Separation](https://mlsanity.com/paper/2211.08303/) (2022)

## Abstract (arXiv)

Separating an audio scene into isolated sources is a fundamental problem in computer audition, analogous to image segmentation in visual scene analysis. Source separation systems based on deep learning are currently the most successful approaches for solving the underdetermined separation problem, where there are more sources than channels. Traditionally, such systems are trained on sound mixtures where the ground truth decomposition is already known. Since most real-world recordings do not have such a decomposition available, this limits the range of mixtures one can train on, and the range of mixtures the learned models may successfully separate. In this work, we use a simple blind spatial source separation algorithm to generate estimated decompositions of stereo mixtures. These estimates, together with a weighting scheme in the time-frequency domain, based on confidence in the separation quality, are used to train a deep learning model that can be used for single-channel separation, where no source direction information is available. This demonstrates how a simple cue such as the direction of origin of source can be used to bootstrap a model for source separation that can be used in situations where that cue is not available.