PhiNet: Speaker Verification with Phonetic Interpretability

TL;DR

PhiNet is a speaker verification model that emphasizes phonetic interpretability, providing transparent decision explanations while maintaining competitive verification accuracy across multiple benchmark datasets.

Contribution

It introduces a novel phonetic interpretability framework for speaker verification, enabling detailed analysis and transparency in decision-making processes.

Findings

PhiNet achieves verification performance comparable to traditional models.

It offers meaningful phonetic explanations for verification decisions.

The model enhances interpretability without sacrificing accuracy.

Abstract

Despite remarkable progress, automatic speaker verification (ASV) systems typically lack the transparency required for high-accountability applications. Motivated by how human experts perform forensic speaker comparison (FSC), we propose a speaker verification network with phonetic interpretability, PhiNet, designed to enhance both local and global interpretability by leveraging phonetic evidence in decision-making. For users, PhiNet provides detailed phonetic-level comparisons that enable manual inspection of speaker-specific features and facilitate a more critical evaluation of verification outcomes. For developers, it offers explicit reasoning behind verification decisions, simplifying error tracing and informing hyperparameter selection. In our experiments, we demonstrate PhiNet's interpretability with practical examples, including its application in analyzing the impact of different hyperparameters. We conduct both qualitative and quantitative evaluations of the proposed interpretability methods and assess speaker verification performance across multiple benchmark datasets, including VoxCeleb, SITW, and LibriSpeech. Results show that PhiNet achieves performance comparable to traditional black-box ASV models while offering meaningful, interpretable explanations for its decisions, bridging the gap between ASV and forensic analysis.