# SLOGD: Speaker LOcation Guided Deflation approach to speech separation

arXiv: https://arxiv.org/abs/1910.11131 · HTML: https://mlsanity.com/paper/1910.11131/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 24 Oct 2019.

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

- [DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF](https://mlsanity.com/paper/2207.10934/) (2022)

## Abstract (arXiv)

Speech separation is the process of separating multiple speakers from an audio recording. In this work we propose to separate the sources using a Speaker LOcalization Guided Deflation (SLOGD) approach wherein we estimate the sources iteratively. In each iteration we first estimate the location of the speaker and use it to estimate a mask corresponding to the localized speaker. The estimated source is removed from the mixture before estimating the location and mask of the next source. Experiments are conducted on a reverberated, noisy multichannel version of the well-studied WSJ-2MIX dataset using word error rate (WER) as a metric. The proposed method achieves a WER of 44.2%, a 34% relative improvement over the system without separation and 17% relative improvement over Conv-TasNet.