Enhancing Age-Related Robustness in Children Speaker Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shetty, Vishwas M., Zheng, Jiusi, Lulich, Steven M., Alwan, Abeer
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913691459387392
author Shetty, Vishwas M.
Zheng, Jiusi
Lulich, Steven M.
Alwan, Abeer
author_facet Shetty, Vishwas M.
Zheng, Jiusi
Lulich, Steven M.
Alwan, Abeer
contents One of the main challenges in children's speaker verification (C-SV) is the significant change in children's voices as they grow. In this paper, we propose two approaches to improve age-related robustness in C-SV. We first introduce a Feature Transform Adapter (FTA) module that integrates local patterns into higher-level global representations, reducing overfitting to specific local features and improving the inter-year SV performance of the system. We then employ Synthetic Audio Augmentation (SAA) to increase data diversity and size, thereby improving robustness against age-related changes. Since the lack of longitudinal speech datasets makes it difficult to measure age-related robustness of C-SV systems, we introduce a longitudinal dataset to assess inter-year verification robustness of C-SV systems. By integrating both of our proposed methods, the average equal error rate was reduced by 19.4%, 13.0%, and 6.1% in the one-year, two-year, and three-year gap inter-year evaluation sets, respectively, compared to the baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Age-Related Robustness in Children Speaker Verification
Shetty, Vishwas M.
Zheng, Jiusi
Lulich, Steven M.
Alwan, Abeer
Audio and Speech Processing
Sound
One of the main challenges in children's speaker verification (C-SV) is the significant change in children's voices as they grow. In this paper, we propose two approaches to improve age-related robustness in C-SV. We first introduce a Feature Transform Adapter (FTA) module that integrates local patterns into higher-level global representations, reducing overfitting to specific local features and improving the inter-year SV performance of the system. We then employ Synthetic Audio Augmentation (SAA) to increase data diversity and size, thereby improving robustness against age-related changes. Since the lack of longitudinal speech datasets makes it difficult to measure age-related robustness of C-SV systems, we introduce a longitudinal dataset to assess inter-year verification robustness of C-SV systems. By integrating both of our proposed methods, the average equal error rate was reduced by 19.4%, 13.0%, and 6.1% in the one-year, two-year, and three-year gap inter-year evaluation sets, respectively, compared to the baseline.
title Enhancing Age-Related Robustness in Children Speaker Verification
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2502.10511