Range-Based Equal Error Rate for Spoof Localization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Range-Based Equal Error Rate for Spoof Localization

Résumé

Spoof localization, also called segment-level detection, is a crucial task that aims to locate spoofs in partially spoofed audio. The equal error rate (EER) is widely used to measure performance for such biometric scenarios. Although EER is the only threshold-free metric, it is usually calculated in a point-based way that uses scores and references with a pre-defined temporal resolution and counts the number of misclassified segments. Such point-based measurement overly relies on this resolution and may not accurately measure misclassified ranges. To properly measure misclassified ranges and better evaluate spoof localization performance, we upgrade point-based EER to range-based EER. Then, we adapt the binary search algorithm for calculating range-based EER and compare it with the classical point-based EER. Our analyses suggest utilizing either range-based EER, or point-based EER with a proper temporal resolution can fairly and properly evaluate the performance of spoof localization.

Dates et versions

hal-04121038 , version 1 (07-06-2023)

Identifiants

Citer

Lin Zhang, Xin Wang, Erica Cooper, Nicholas Evans, Junichi Yamagishi. Range-Based Equal Error Rate for Spoof Localization. INTERSPEECH 2023, 24th Conference of the International Speech Communication Association, Aug 2023, Dublin, Ireland. ⟨hal-04121038⟩

Collections

EURECOM ANR
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More