Saved in:
Bibliographic Details
Main Authors: Wang, Rui, Zhang, Zhifei, Gao, Yu, Mou, Xiaofeng, Xu, Yi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09505
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912958661001216
author Wang, Rui
Zhang, Zhifei
Gao, Yu
Mou, Xiaofeng
Xu, Yi
author_facet Wang, Rui
Zhang, Zhifei
Gao, Yu
Mou, Xiaofeng
Xu, Yi
contents Keyword spotting (KWS) is crucial for many speech-driven applications, but robust KWS in noisy environments remains challenging. Conventional systems often rely on single-channel inputs and a cascaded pipeline separating front-end enhancement from KWS. This precludes joint optimization, inherently limiting performance. We present an end-to-end multi-channel KWS framework that exploits spatial cues to improve noise robustness. A spatial encoder learns inter-channel features, while a spatial embedding injects directional priors; the fused representation is processed by a streaming backbone. Experiments in simulated noisy conditions across multiple signal-to-noise ratios (SNRs) show that spatial modeling and directional priors each yield clear gains over baselines, with their combination achieving the best results. These findings validate end-to-end multi-channel spatial modeling, indicating strong potential for the target-speaker-aware detection in complex acoustic scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09505
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle End-to-End Direction-Aware Keyword Spotting with Spatial Priors in Noisy Environments
Wang, Rui
Zhang, Zhifei
Gao, Yu
Mou, Xiaofeng
Xu, Yi
Audio and Speech Processing
Keyword spotting (KWS) is crucial for many speech-driven applications, but robust KWS in noisy environments remains challenging. Conventional systems often rely on single-channel inputs and a cascaded pipeline separating front-end enhancement from KWS. This precludes joint optimization, inherently limiting performance. We present an end-to-end multi-channel KWS framework that exploits spatial cues to improve noise robustness. A spatial encoder learns inter-channel features, while a spatial embedding injects directional priors; the fused representation is processed by a streaming backbone. Experiments in simulated noisy conditions across multiple signal-to-noise ratios (SNRs) show that spatial modeling and directional priors each yield clear gains over baselines, with their combination achieving the best results. These findings validate end-to-end multi-channel spatial modeling, indicating strong potential for the target-speaker-aware detection in complex acoustic scenarios.
title End-to-End Direction-Aware Keyword Spotting with Spatial Priors in Noisy Environments
topic Audio and Speech Processing
url https://arxiv.org/abs/2603.09505