# VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark

arXiv: https://arxiv.org/abs/2407.11510 · HTML: https://mlsanity.com/paper/2407.11510/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2024.

## Built on by (most cited first, 26 of 26)

- [The First VoicePrivacy Attacker Challenge](https://mlsanity.com/paper/2504.14183/) (2025)
- [The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition](https://mlsanity.com/paper/2505.13971/) (2025)
- [Holistic Uncertainty Estimation For Open-Set Recognition](https://mlsanity.com/paper/2408.14229/) (2024)
- [FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for "U-Tsang, Amdo and Kham Speech Dataset Generation](https://mlsanity.com/paper/2505.14351/) (2025)
- [Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning](https://mlsanity.com/paper/2510.04213/) (2025)
- [Scores Know Bobs Voice: Speaker Impersonation Attack](https://mlsanity.com/paper/2603.02781/) (2026)
- [The First VoicePrivacy Attacker Challenge Evaluation Plan](https://mlsanity.com/paper/2410.07428/) (2024)
- [Interpolating Speaker Identities in Embedding Space for Data Expansion](https://mlsanity.com/paper/2508.19210/) (2025)
- [DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model](https://mlsanity.com/paper/2510.17662/) (2025)
- [What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification](https://mlsanity.com/paper/2603.24432/) (2026)
- [POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan](https://mlsanity.com/paper/2603.24569/) (2026)
- [FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition](https://mlsanity.com/paper/2606.06211/) (2026)
- [AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification](https://mlsanity.com/paper/2606.29335/) (2026)
- [Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models](https://mlsanity.com/paper/2506.13300/) (2025)
- [Comparison of End-to-end Speech Assessment Models for the NOCASA 2025 Challenge](https://mlsanity.com/paper/2509.03256/) (2025)
- [Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities](https://mlsanity.com/paper/2512.14961/) (2025)
- [Self-Supervised Learning for Speaker Recognition: A study and review](https://mlsanity.com/paper/2602.10829/) (2026)
- [Uncertainty Estimation for the Open-Set Text Classification systems](https://mlsanity.com/paper/2604.08560/) (2026)
- [L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification](https://mlsanity.com/paper/2606.17416/) (2026)
- [ZONOS2 Technical Report](https://mlsanity.com/paper/2606.24320/) (2026)
- [Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge](https://mlsanity.com/paper/2607.13669/) (2026)
- [Simple Language Normalization Wins: Cross-Lingual Speaker Verification for the TidyVoice 2026 Challenge](https://mlsanity.com/paper/2607.22923/) (2026)
- [Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge](https://mlsanity.com/paper/2609.20833/) (2026)
- [MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification](https://mlsanity.com/paper/2609.24061/) (2026)
- [Mixed-Prior Decision Risk for Open-Set Recognition](https://mlsanity.com/paper/2609.35043/) (2026)
- [FASTDIAR: Frame-level speaker encoder for Streaming Diarization](https://mlsanity.com/paper/2610.02941/) (2026)

## Abstract (arXiv)

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 http://voxblink2.github.io.