Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908929931345920 |
|---|---|
| author | Qu, Yangyang Todisco, Massimiliano Galdi, Chiara Evans, Nicholas |
| author_facet | Qu, Yangyang Todisco, Massimiliano Galdi, Chiara Evans, Nicholas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11360 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics Qu, Yangyang Todisco, Massimiliano Galdi, Chiara Evans, Nicholas Sound Audio and Speech Processing 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. |
| title | Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.11360 |