Saved in:
Bibliographic Details
Main Authors: Li, Jiatong, Middelberg, Wiebke, Doclo, Simon
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.18442
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914578264227840
author Li, Jiatong
Middelberg, Wiebke
Doclo, Simon
author_facet Li, Jiatong
Middelberg, Wiebke
Doclo, Simon
contents Recently, a spatially selective non-linear filter (SSF) has been proposed for target speaker extraction, using the target direction-of-arrival (DOA) as a spatial cue. Since learned intermediate features are tied to the microphone geometry, the performance of the SSF degrades significantly when evaluated on mismatched array geometries. In this paper, we propose a geometry-conditioned SSF (GC-SSF), which incorporates a geometry-conditioning branch based on FiLM layers. Furthermore, we propose a feature that jointly encodes the DOA and the microphone positions (DOA-MPE). The conditioning branch modulates the intermediate feature maps of the SSF using the DOA-MPE feature to capture the spatial relationship between the microphone positions and the target speaker. Experimental results across circular, uniform linear, and random microphone arrays show that the proposed GC-SSF generalizes better to mismatched geometries while maintaining high spatial selectivity, demonstrating its ability to effectively adapt the filtering process to different array geometries
format Preprint
id arxiv_https___arxiv_org_abs_2605_18442
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Flexible Multi-Channel Target Speaker Extraction Using Geometry-Conditioned Spatially Selective Non-linear Filters
Li, Jiatong
Middelberg, Wiebke
Doclo, Simon
Audio and Speech Processing
Recently, a spatially selective non-linear filter (SSF) has been proposed for target speaker extraction, using the target direction-of-arrival (DOA) as a spatial cue. Since learned intermediate features are tied to the microphone geometry, the performance of the SSF degrades significantly when evaluated on mismatched array geometries. In this paper, we propose a geometry-conditioned SSF (GC-SSF), which incorporates a geometry-conditioning branch based on FiLM layers. Furthermore, we propose a feature that jointly encodes the DOA and the microphone positions (DOA-MPE). The conditioning branch modulates the intermediate feature maps of the SSF using the DOA-MPE feature to capture the spatial relationship between the microphone positions and the target speaker. Experimental results across circular, uniform linear, and random microphone arrays show that the proposed GC-SSF generalizes better to mismatched geometries while maintaining high spatial selectivity, demonstrating its ability to effectively adapt the filtering process to different array geometries
title Flexible Multi-Channel Target Speaker Extraction Using Geometry-Conditioned Spatially Selective Non-linear Filters
topic Audio and Speech Processing
url https://arxiv.org/abs/2605.18442