Research

Paper

TESTING March 11, 2026

Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Authors

Yangyang Qu, Todisco Massimiliano, Galdi Chiara, Evans Nicholas

Abstract

Voice biometric systems can exhibit sex-related performance gaps even when overall verification accuracy is strong. We attribute these gaps to two practical mechanisms: (i) demographic shortcut learning, where speaker classification training exploits spurious correlations between sex and speaker identity, and (ii) feature entanglement, where sex-linked acoustic variation overlaps with identity cues and cannot be removed without degrading speaker discrimination. We propose Fair-Gate, a fairness-aware and interpretable risk-gating framework that addresses both mechanisms in a single pipeline. Fair-Gate applies risk extrapolation to reduce variation in speaker-classification risk across proxy sex groups, and introduces a local complementary gate that routes intermediate features into an identity branch and a sex branch. The gate provides interpretability by producing an explicit routing mask that can be inspected to understand which features are allocated to identity versus sex-related pathways. Experiments on VoxCeleb1 show that Fair-Gate improves the utility--fairness trade-off, yielding more sex-fair ASV performance under challenging evaluation conditions.

Metadata

arXiv ID: 2603.11360
Provider: ARXIV
Primary Category: cs.SD
Published: 2026-03-11
Fetched: 2026-03-13 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11360v1</id>\n    <title>Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics</title>\n    <updated>2026-03-11T22:50:15Z</updated>\n    <link href='https://arxiv.org/abs/2603.11360v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11360v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Voice biometric systems can exhibit sex-related performance gaps even when overall verification accuracy is strong. We attribute these gaps to two practical mechanisms: (i) demographic shortcut learning, where speaker classification training exploits spurious correlations between sex and speaker identity, and (ii) feature entanglement, where sex-linked acoustic variation overlaps with identity cues and cannot be removed without degrading speaker discrimination. We propose Fair-Gate, a fairness-aware and interpretable risk-gating framework that addresses both mechanisms in a single pipeline. Fair-Gate applies risk extrapolation to reduce variation in speaker-classification risk across proxy sex groups, and introduces a local complementary gate that routes intermediate features into an identity branch and a sex branch. The gate provides interpretability by producing an explicit routing mask that can be inspected to understand which features are allocated to identity versus sex-related pathways. Experiments on VoxCeleb1 show that Fair-Gate improves the utility--fairness trade-off, yielding more sex-fair ASV performance under challenging evaluation conditions.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SD'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.AS'/>\n    <published>2026-03-11T22:50:15Z</published>\n    <arxiv:primary_category term='cs.SD'/>\n    <author>\n      <name>Yangyang Qu</name>\n    </author>\n    <author>\n      <name>Todisco Massimiliano</name>\n    </author>\n    <author>\n      <name>Galdi Chiara</name>\n    </author>\n    <author>\n      <name>Evans Nicholas</name>\n    </author>\n  </entry>"
}