Voxceleb2: Deep Speaker Recognition

Abstract

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 audio-visual 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.

Stats

• citations1563
• S2 citations—
• github stars0
• HF likes0
• heat score23.96
• arxiv keychung2018voxceleb2

Related papers

• Voxceleb: A Large-scale Speaker Identification Dataset (2017)23.55
• Voxsrc 2019: The First Voxceleb Speaker Recognition Challenge (2019)0.00
• The Ins And Outs Of Speaker Recognition: Lessons From Voxsrc 2020 (2020)11.85
• Voxblink2: A 100K+ Speaker Recognition Corpus And The Open-set Speaker-identification Benchmark (2024)9.41
• CN-CELEB: A Challenging Chinese Speaker Recognition Dataset (2019)16.39
• Delving Into Voxceleb: Environment Invariant Speaker Recognition (2019)10.35
• Voxsrc 2020: The Second Voxceleb Speaker Recognition Challenge (2020)0.00
• Voxceleb-esp: Preliminary Experiments Detecting Spanish Celebrities From Their Voices (2023)0.00