PhiNet: Speaker Verification With Phonetic Interpretability

Yi Ma

doi:10.1109/TASLPRO.2025.3642540

PhiNet: Speaker Verification With Phonetic Interpretability

2026-01-01

1

PRE

AI

DOI：10.1109/TASLPRO.2025.3642540

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Phonetics

Power capacitors

Training

Forensics

Analytical models

Speaker recognition

Closed box

Biological neural networks

Decision making

Spectrogram

Speaker verification

interpretability

forensic speaker comparison

phonetic

XAI

PhiNet: Speaker Verification With Phonetic Interpretability

Abstract

Journal

Organization