The objective of this paper is speaker recognition under noisy and unconstrained conditions. We make two key contributions. First, we introduce a very large-scale speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset. Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice under various conditions. The models trained on the VoxCeleb2 dataset surpass the performance of previous works on a benchmark dataset by a significant margin.
Cite as: Chung, J.S., Nagrani, A., Zisserman, A. (2018) VoxCeleb2: Deep Speaker Recognition. Proc. Interspeech 2018, 1086-1090, doi: 10.21437/Interspeech.2018-1929
@inproceedings{chung18b_interspeech,
author={Joon Son Chung and Arsha Nagrani and Andrew Zisserman},
title={{VoxCeleb2: Deep Speaker Recognition}},
year=2018,
booktitle={Proc. Interspeech 2018},
pages={1086--1090},
doi={10.21437/Interspeech.2018-1929}
}