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

Page view(s)
30
Checked on Feb 14, 2025
Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing
Title:
Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing
Journal Title:
Interspeech 2021
Publication Date:
30 August 2021
Citation:
Kinnunen, T., Nautsch, A., Sahidullah, M., Evans, N., Wang, X., Todisco, M., … Lee, K. A. (2021). Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing. Interspeech 2021. doi:10.21437/interspeech.2021-1522
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.
License type:
Publisher Copyright
Funding Info:
This work was supported by a number of projects and funding sources: VoicePersonae, supported by the French Agence Nationale de la Recherche (ANR) and the Japan Science and Technology Agency (JST) with grant No. JPMJCR18A6; Academy of Finland (proj. 309629); Region Grand Est, France.
Description:
ISSN:
1990-9772
Files uploaded:

File Size Format Action
kinnunen21-interspeech.pdf 512.31 KB PDF Open