# Enhanced Reverberation as Supervision for Unsupervised Speech Separation

arXiv: https://arxiv.org/abs/2408.03438 · HTML: https://mlsanity.com/paper/2408.03438/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2024.

## Built on by (most cited first, 1 of 1)

- [ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior](https://mlsanity.com/paper/2505.05657/) (2025)

## Abstract (arXiv)

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an input channel can be mapped to reconstruct a mixture at a target channel. However, stable unsupervised training has so far only been achieved in over-determined source-channel conditions, leaving the key determined case unsolved. This work proposes enhanced RAS (ERAS) for solving this problem. Through qualitative analysis, we found that stable training can be achieved by leveraging the loss term to alleviate the frequency-permutation problem. Separation performance is also boosted by adding a novel loss term where separated signals mapped back to their own input mixture are used as pseudo-targets for the signals separated from other channels and mapped to the same channel. Experimental results demonstrate high stability and performance of ERAS.