Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing

TL;DR

This paper introduces a visualization method for comparing classifiers by creating 2D representations based on rank correlations, aiding analysis in speaker verification and voice anti-spoofing.

Contribution

The paper presents a novel, versatile visualization technique that enables comparison of classifier behaviors using score data, applicable across detection tasks.

Findings

Effective visualization of classifier relations using rank correlation-based 2D plots.

Application to speaker verification and voice anti-spoofing demonstrates utility.

Facilitates insights into classifier similarity and complementarity.

Abstract

Whether it be for results summarization, or the analysis of classifier fusion, some means to compare different classifiers can often provide illuminating insight into their behaviour, (dis)similarity or complementarity. We propose a simple method to derive 2D representation from detection scores produced by an arbitrary set of binary classifiers in response to a common dataset. Based upon rank correlations, our method facilitates a visual comparison of classifiers with arbitrary scores and with close relation to receiver operating characteristic (ROC) and detection error trade-off (DET) analyses. While the approach is fully versatile and can be applied to any detection task, we demonstrate the method using scores produced by automatic speaker verification and voice anti-spoofing systems. The former are produced by a Gaussian mixture model system trained with VoxCeleb data whereas the latter stem from submissions to the ASVspoof 2019 challenge.