Voxblink2: A 100K+ Speaker Recognition Corpus And The Open-set Speaker-identification Benchmark

Abstract

In this paper, we provide a large audio-visual speaker recognition dataset, VoxBlink2, which includes approximately 10M utterances with videos from 110K+ speakers in the wild. This dataset represents a significant expansion over the VoxBlink dataset, encompassing a broader diversity of speakers and scenarios by the grace of an optimized data collection pipeline. Afterward, we explore the impact of training strategies, data scale, and model complexity on speaker verification and finally establish a new single-model state-of-the-art EER at 0.170% and minDCF at 0.006% on the VoxCeleb1-O test set. Such remarkable results motivate us to explore speaker recognition from a new challenging perspective. We raise the Open-Set Speaker-Identification task, which is designed to either match a probe utterance with a known gallery speaker or categorize it as an unknown query. Associated with this task, we design concrete benchmark and evaluation protocols. The data and model resources can be found in

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keylin2024voxblink2

Related papers

• Voxceleb: A Large-scale Speaker Identification Dataset (2017)23.55
• Voxceleb2: Deep Speaker Recognition (2018)23.96
• Voxsrc 2019: The First Voxceleb Speaker Recognition Challenge (2019)0.00
• Voxsrc 2020: The Second Voxceleb Speaker Recognition Challenge (2020)0.00
• The DKU-MSXF Speaker Verification System For The Voxceleb Speaker Recognition Challenge 2023 (2023)0.00
• Voxceleb-esp: Preliminary Experiments Detecting Spanish Celebrities From Their Voices (2023)0.00
• CN-CELEB: A Challenging Chinese Speaker Recognition Dataset (2019)16.39
• Voxlingua107: A Dataset For Spoken Language Recognition (2020)14.15