Range-Based Equal Error Rate for Spoof Localization

• URL: http://arxiv.org/abs/2305.17739v1
• Date: Sun, 28 May 2023 14:46:54 GMT
• Title: Range-Based Equal Error Rate for Spoof Localization
• Authors: Lin Zhang, Xin Wang, Erica Cooper, Nicholas Evans, Junichi Yamagishi
• Abstract summary: Spoof localization 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. We upgrade point-based EER to range-based EER and compare it with the classical point-based EER.
• Score: 43.75986914767975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Towards Unbiased Evaluation of Time-series Anomaly Detector [6.521243384420707]
  Time series anomaly detection (TSAD) is an evolving area of research motivated by its critical applications. In this work, we propose an alternative adjustment protocol called Balanced point adjustment'' (BA)
  arXiv  Detail & Related papers  (2024-09-19T19:02:45Z)
• Improving Interpretability of Scores in Anomaly Detection Based on Gaussian-Bernoulli Restricted Boltzmann Machine [0.0]
  In GBRBM-based anomaly detection, normal and anomalous data are classified based on a score that is identical to an energy function of the marginal GBRBM. We propose a measure that improves score's interpretability based on its cumulative distribution. We also establish a guideline for setting the threshold using the interpretable measure.
  arXiv  Detail & Related papers  (2024-03-19T12:13:52Z)
• Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [54.23513799338309]
  We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition. Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
  arXiv  Detail & Related papers  (2022-09-21T02:33:07Z)
• Comparison of Evaluation Metrics for Landmark Detection in CMR Images [0.8219153654616499]
  We extend the public ACDC dataset with additional labels of the right ventricular insertion points. We compare different variants of a heatmap-based landmark detection pipeline. Preliminary results indicate that a combination of different metrics is necessary.
  arXiv  Detail & Related papers  (2022-01-25T15:58:30Z)
• Ordinal UNLOC: Target Localization with Noisy and Incomplete Distance Measures [1.6836876499886007]
  A main challenge in target localization arises from the lack of reliable distance measures. We develop a new computational framework to estimate the location of a target without the need for reliable distance measures.
  arXiv  Detail & Related papers  (2021-05-06T13:54:31Z)
• Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details [107.2722027807328]
  We find that the default implementation of AP is neither category independent, nor does it directly reward properly calibrated detectors. We show that the default implementation produces a gameable metric, where a simple, nonsensical re-ranking policy can improve AP by a large margin. We benchmark recent advances in large-vocabulary detection and find that many reported gains do not translate to improvements under our new per-class independent evaluation.
  arXiv  Detail & Related papers  (2021-02-01T18:56:02Z)
• AP-Loss for Accurate One-Stage Object Detection [49.13608882885456]
  One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously. The former suffers much from extreme foreground-background imbalance due to the large number of anchors. This paper proposes a novel framework to replace the classification task in one-stage detectors with a ranking task.
  arXiv  Detail & Related papers  (2020-08-17T13:22:01Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)
• Scope Head for Accurate Localization in Object Detection [135.9979405835606]
  We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
  arXiv  Detail & Related papers  (2020-05-11T04:00:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.