Spatially Selective Deep Non-linear Filters for Speaker Extraction

TL;DR

This paper introduces a deep non-linear filtering method that leverages spatial cues for targeted speaker extraction, enabling flexible multi-speaker separation and precise localization without performance loss.

Contribution

It proposes a novel conditioning mechanism for spatially selective deep filters, enhancing flexibility and effectiveness in multi-speaker scenarios.

Findings

Improved speaker extraction accuracy

Effective multi-speaker separation

Accurate multi-speaker localization

Abstract

In a scenario with multiple persons talking simultaneously, the spatial characteristics of the signals are the most distinct feature for extracting the target signal. In this work, we develop a deep joint spatial-spectral non-linear filter that can be steered in an arbitrary target direction. For this we propose a simple and effective conditioning mechanism, which sets the initial state of the filter's recurrent layers based on the target direction. We show that this scheme is more effective than the baseline approach and increases the flexibility of the filter at no performance cost. The resulting spatially selective non-linear filters can also be used for speech separation of an arbitrary number of speakers and enable very accurate multi-speaker localization as we demonstrate in this paper.