VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge

Jaesung Huh, Andrew Brown, Jee-weon Jung, Joon Son Chung, Arsha Nagrani +2 more
2/20/2023
cs.SDcs.LGeess.AS

No official code found. Best implementation: JaesungHuh/VoxSRC2022 (19 stars, last commit 2022-07-21).

Abstract

This paper summarises the findings from the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22), which was held in conjunction with INTERSPEECH 2022. The goal of this challenge was to evaluate how well state-of-the-art speaker recognition systems can diarise and recognise speakers from speech obtained "in the wild". The challenge consisted of: (i) the provision of publicly available speaker recognition and diarisation data from YouTube videos together with ground truth annotation and standardised evaluation software; and (ii) a public challenge and hybrid workshop held at INTERSPEECH 2022. We describe the four tracks of our challenge along with the baselines, methods, and results. We conclude with a discussion on the new domain-transfer focus of VoxSRC-22, and on the progression of the challenge from the previous three editions.

View on arXivView PDF

Code Implementations(1)

JaesungHuh/VoxSRC2022Community100%

VoxSRC2022 workshop development kit

190Perl, PythonJul 9, 20224 years ago

Similar Papers

The VoxCeleb Speaker Recognition Challenge: A Retrospective

87% match2024

Interpolating Speaker Identities in Embedding Space for Data Expansion

78% match2025

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

77% match2024

The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments

77% match2024

Bilingual Text-dependent Speaker Verification with Pre-trained Models for TdSV Challenge 2024

77% match2024

POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan

77% match2026

Cite this paper

@article{huh2023voxsrc,
  title  = {VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge},
  author = {Jaesung Huh and Andrew Brown and Jee-weon Jung and Joon Son Chung and Arsha Nagrani and Daniel Garcia-Romero and Andrew Zisserman},
  year   = {2023},
  eprint = {2302.10248},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.10248v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.10248.svg)](https://codeofpaper.com/paper/2302.10248)

Discussion