TY - GEN
T1 - Visualizing classifier adjacency relations
T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
AU - Kinnunen, Tomi
AU - Nautsch, Andreas
AU - Sahidullah, Md
AU - Evans, Nicholas
AU - Wang, Xin
AU - Todisco, Massimiliano
AU - Delgado, Héctor
AU - Yamagishi, Junichi
AU - Lee, Kong Aik
N1 - Publisher Copyright:
Copyright © 2021 ISCA.
PY - 2021/9
Y1 - 2021/9
N2 - 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.
AB - 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.
KW - Classifier
KW - Multi-dimensional scaling
UR - https://www.scopus.com/pages/publications/85119249123
U2 - 10.21437/Interspeech.2021-1522
DO - 10.21437/Interspeech.2021-1522
M3 - Conference article published in proceeding or book
AN - SCOPUS:85119249123
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 4675
EP - 4679
BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PB - International Speech Communication Association
Y2 - 30 August 2021 through 3 September 2021
ER -