ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan

View on arXiv ← Back to list

Authors: Héctor Delgado, Nicholas Evans, Tomi Kinnunen, Kong Aik Lee, Xuechen Liu, Andreas Nautsch, Jose Patino, Md Sahidullah, Massimiliano Todisco, Xin Wang, Junichi Yamagishi

Published: 2021-09-01 15:32:28+00:00

AI Summary

The ASVspoof 2021 challenge focuses on developing spoofing countermeasures for speech data, encompassing logical access (LA), physical access (PA), and speech deepfake (DF) tasks. The paper details the challenge's evaluation plan, including datasets, metrics (t-DCF and EER), and baseline systems.

Abstract

The automatic speaker verification spoofing and countermeasures (ASVspoof) challenge series is a community-led initiative which aims to promote the consideration of spoofing and the development of countermeasures. ASVspoof 2021 is the 4th in a series of bi-annual, competitive challenges where the goal is to develop countermeasures capable of discriminating between bona fide and spoofed or deepfake speech. This document provides a technical description of the ASVspoof 2021 challenge, including details of training, development and evaluation data, metrics, baselines, evaluation rules, submission procedures and the schedule.

Key findings

UNKNOWN (The paper describes the challenge setup, not results. Results would be determined after the competition.)

Approach

The challenge involves developing countermeasures that discriminate between bona fide and spoofed speech across various scenarios (LA, PA, DF). Participants use ASVspoof 2019 data for training and development, applying their systems to new evaluation data and submitting scores for evaluation.

Datasets

ASVspoof 2019 training and development data; new evaluation data for ASVspoof 2021 (LA, PA, DF tasks). VoxCeleb data (for baseline ASV system).

Model(s)

Baseline models included LFCC-GMM, CQCC-GMM, LFCC-LCNN, and RawNet2. Participants could use any approach.

Author countries

UNKNOWN

← Previous