Learning Emotion-Invariant Speaker Representations for Speaker Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Jingguang, Hu, Xinhui, Xu, Xinkang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916756455424000
author Tian, Jingguang
Hu, Xinhui
Xu, Xinkang
author_facet Tian, Jingguang
Hu, Xinhui
Xu, Xinkang
contents In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To address this issue, we propose multiple improvements to train speaker encoders to increase emotion robustness. Firstly, we utilize CopyPaste-based data augmentation to gather additional parallel data, which includes different emotional expressions from the same speaker. Secondly, we apply cosine similarity loss to restrict parallel sample pairs and minimize intra-class variation of speaker representations to reduce their correlation with emotional information. Finally, we use emotion-aware masking (EM) based on the speech signal energy on the input parallel samples to further strengthen the speaker representation and make it emotion-invariant. We conduct a comprehensive ablation study to demonstrate the effectiveness of these various components. Experimental results show that our proposed method achieves a relative 19.29\% drop in EER compared to the baseline system.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Emotion-Invariant Speaker Representations for Speaker Verification
Tian, Jingguang
Hu, Xinhui
Xu, Xinkang
Sound
Audio and Speech Processing
In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To address this issue, we propose multiple improvements to train speaker encoders to increase emotion robustness. Firstly, we utilize CopyPaste-based data augmentation to gather additional parallel data, which includes different emotional expressions from the same speaker. Secondly, we apply cosine similarity loss to restrict parallel sample pairs and minimize intra-class variation of speaker representations to reduce their correlation with emotional information. Finally, we use emotion-aware masking (EM) based on the speech signal energy on the input parallel samples to further strengthen the speaker representation and make it emotion-invariant. We conduct a comprehensive ablation study to demonstrate the effectiveness of these various components. Experimental results show that our proposed method achieves a relative 19.29\% drop in EER compared to the baseline system.
title Learning Emotion-Invariant Speaker Representations for Speaker Verification
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.18498