Text-dependent Speaker Verification (TdSV) Challenge 2024: Challenge Evaluation Plan

This document outlines the Text-dependent Speaker Verification (TdSV) Challenge 2024, which centers on analyzing and exploring novel approaches for text-dependent speaker verification. The primary goal of this challenge is to motive participants to develop single yet competitive systems, conduct thorough analyses, and explore innovative concepts such as multi-task learning, self-supervised learning, few-shot learning, and others, for text-dependent speaker verification. Building upon the achievements of the Short-duration Speaker Verification (SdSV) Challenge 2020 and 2021, the TdSV Challenge 2024 focuses exclusively on text-dependent verification in two distinct scenarios. The first scenario involves conventional TdSV, while the second track entails speaker enrollment using user-defined passphrases. The evaluation dataset utilized for the challenge is derived from the second version of the versatile DeepMine dataset [1, 2]. For this challenge, Parts 1 and 3 of the dataset are employed. The subsequent section provides a comprehensive description of both tasks.