Inclusive Speaker Verification with Adaptive thresholding

TL;DR

This paper introduces an adaptive thresholding framework for speaker verification that accounts for gender and age, improving inclusivity by reducing false rejection rates across diverse user groups.

Contribution

It proposes a novel context-adaptive thresholding method and a concatenated gender/age detection model to enhance speaker verification fairness and performance.

Findings

Reduced FRR for specific gender groups at a fixed FAR on VoxCeleb1.

Significant FRR reduction for certain age groups on OGI Kids' Speech corpus.

Effective use of prior information and derived context improves SV system inclusivity.

Abstract

While using a speaker verification (SV) based system in a commercial application, it is important that customers have an inclusive experience irrespective of their gender, age, or ethnicity. In this paper, we analyze the impact of gender and age on SV and find that for a desired common False Acceptance Rate (FAR) across different gender and age groups, the False Rejection Rate (FRR) is different for different gender and age groups. To optimize FRR for all users for a desired FAR, we propose a context (e.g. gender, age) adaptive thresholding framework for SV. The context can be available as prior information for many practical applications. We also propose a concatenated gender/age detection model to algorithmically derive the context in absence of such prior information. We experimentally show that our context-adaptive thresholding method is effective in building a more efficient inclusive SV system. Specifically, we show that we can reduce FRR for specific gender for a desired FAR on the voxceleb1 test set by using gender-specific thresholds. Similar analysis on OGI kids' speech corpus shows that by using an age-specific threshold, we can significantly reduce FRR for certain age groups for desired FAR.