Datasets › VoxCeleb2
VoxCeleb2
VoxCeleb2 is a large scale speaker recognition dataset obtained automatically from open-source media. VoxCeleb2 consists of over a million utterances from over 6k speakers. Since the dataset is collected ‘in the wild’, the speech segments are corrupted with real world noise including laughter, cross-talk, channel effects, music and other sounds. The dataset is also multilingual, with speech from speakers of 145 different nationalities, covering a wide range of accents, ages, ethnicities and languages. The dataset is audio-visual, so is also useful for a number of other applications, for example – visual speech synthesis, speech separation, cross-modal transfer from face to voice or vice versa and training face recognition from video to complement existing face recognition datasets.
Source: VoxCeleb2: Deep Speaker Recognition Image Source: https://www.robots.ox.ac.uk/~vgg/data/voxceleb/
Benchmarks archive 2025-07-28
All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Speech Separation | VoxCeleb2 | IIANet SI-SNRi 14.0 | IIANet: An Intra- and Inter-Modality Attention Network... | JusperLee/IIANet | 5 | Compare |
| Talking Head Generation | VoxCeleb2 - 1-shot learning | Fast Bi-layer Avatars (medium size) CSIM 0.653 | Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars | saic-violet/bilayer-model | 5 | Compare |
| Talking Head Generation | VoxCeleb2 - 8-shot learning | CainGAN FID 24.9 | Pose Manipulation with Identity Preservation | — | 2 | Compare |
| Speaker Verification | VoxCeleb2 | ResNet-50 EER 100 | VoxCeleb2: Deep Speaker Recognition | a-nagrani/VGGVox +1 | 1 | Compare |
| Talking Head Generation | VoxCeleb2 - 32-shot learning | Few-shot Adversarial Model FID 30.6 | Few-Shot Adversarial Learning of Realistic Neural... | vincent-thevenin/Realistic-Neural-Talking-Head-Models +5 | 1 | Compare |
Papers archive 2025-07-28
papers with a benchmark row: 7 · with a code link: 6 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all papers with a benchmark rowonly where code ran (4 of 7 with a benchmark row: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 7 of 7 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).
The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 564. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- VoxCeleb2 - 1-shot learning
- VoxCeleb2 - 8-shot learning
- VoxCeleb2 - 32-shot learning
- VoxCeleb2
4 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections