Saved in:
Bibliographic Details
Main Authors: Huang, Zijun, Liang, Chengdong, Yao, Jiadi, Zhang, Xiao-Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912545690877952
author Huang, Zijun
Liang, Chengdong
Yao, Jiadi
Zhang, Xiao-Lei
author_facet Huang, Zijun
Liang, Chengdong
Yao, Jiadi
Zhang, Xiao-Lei
contents The presence of non-speech segments in utterances often leads to the performance degradation of speaker verification. Existing systems usually use voice activation detection as a preprocessing step to cut off long silence segments. However, short silence segments, particularly those between speech segments, still remain a problem for speaker verification. To address this issue, in this paper, we propose a simple wave-level data augmentation method, \textit{PadAug}, which aims to enhance the system's robustness to silence segments. The core idea of \textit{PadAug} is to concatenate silence segments with speech segments at the waveform level for model training. Due to its simplicity, it can be directly applied to the current state-of-the art architectures. Experimental results demonstrate the effectiveness of the proposed \textit{PadAug}. For example, applying \textit{PadAug} to ResNet34 achieves a relative equal error rate reduction of 5.0\% on the voxceleb dataset. Moreover, the \textit{PadAug} based systems are robust to different lengths and proportions of silence segments in the test data.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14732
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PadAug: Robust Speaker Verification with Simple Waveform-Level Silence Padding
Huang, Zijun
Liang, Chengdong
Yao, Jiadi
Zhang, Xiao-Lei
Audio and Speech Processing
The presence of non-speech segments in utterances often leads to the performance degradation of speaker verification. Existing systems usually use voice activation detection as a preprocessing step to cut off long silence segments. However, short silence segments, particularly those between speech segments, still remain a problem for speaker verification. To address this issue, in this paper, we propose a simple wave-level data augmentation method, \textit{PadAug}, which aims to enhance the system's robustness to silence segments. The core idea of \textit{PadAug} is to concatenate silence segments with speech segments at the waveform level for model training. Due to its simplicity, it can be directly applied to the current state-of-the art architectures. Experimental results demonstrate the effectiveness of the proposed \textit{PadAug}. For example, applying \textit{PadAug} to ResNet34 achieves a relative equal error rate reduction of 5.0\% on the voxceleb dataset. Moreover, the \textit{PadAug} based systems are robust to different lengths and proportions of silence segments in the test data.
title PadAug: Robust Speaker Verification with Simple Waveform-Level Silence Padding
topic Audio and Speech Processing
url https://arxiv.org/abs/2508.14732