Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kienegger, Jakob, Gerkmann, Timo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909617524572160
author Kienegger, Jakob
Gerkmann, Timo
author_facet Kienegger, Jakob
Gerkmann, Timo
contents Recent speaker extraction methods using deep non-linear spatial filtering perform exceptionally well when the target direction is known and stationary. However, spatially dynamic scenarios are considerably more challenging due to time-varying spatial features and arising ambiguities, e.g. when moving speakers cross. While in a static scenario it may be easy for a user to point to the target's direction, manually tracking a moving speaker is impractical. Instead of relying on accurate time-dependent directional cues, which we refer to as strong guidance, in this paper we propose a weakly guided extraction method solely depending on the target's initial position to cope with spatial dynamic scenarios. By incorporating our own deep tracking algorithm and developing a joint training strategy on a synthetic dataset, we demonstrate the proficiency of our approach in resolving spatial ambiguities and even outperform a mismatched, but strongly guided extraction method.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14517
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
Kienegger, Jakob
Gerkmann, Timo
Audio and Speech Processing
Machine Learning
Sound
Recent speaker extraction methods using deep non-linear spatial filtering perform exceptionally well when the target direction is known and stationary. However, spatially dynamic scenarios are considerably more challenging due to time-varying spatial features and arising ambiguities, e.g. when moving speakers cross. While in a static scenario it may be easy for a user to point to the target's direction, manually tracking a moving speaker is impractical. Instead of relying on accurate time-dependent directional cues, which we refer to as strong guidance, in this paper we propose a weakly guided extraction method solely depending on the target's initial position to cope with spatial dynamic scenarios. By incorporating our own deep tracking algorithm and developing a joint training strategy on a synthetic dataset, we demonstrate the proficiency of our approach in resolving spatial ambiguities and even outperform a mismatched, but strongly guided extraction method.
title Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2505.14517