VoxCeleb2: Deep Speaker Recognition
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“FakeAVCeleb [53] is a multimodal deepfake dataset constructed from 500 real videos extracted from the VoxCeleb2 corpus [54]. These real videos serve as the basis for generating approximately 20,000 deepfake videos using various deepfake generation techniques.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [54]
The cited source says what the claim attributes to it.
In the citing paper
“The VoxCeleb2 dataset contains over 2,000 h of audio data with real world noise such as background music, laughing and cross-talk. In addition, the dataset is captured from speakers of 145 different nationalities including different accents, ages, ethnicities, and even languages.”
From Audio deepfakes: A survey (2023) · cites this paper as Chung et al., 2018
The cited source says what the claim attributes to it.
In the citing paper
“MelNet (Vasquez and Lewis, 2019), which has used a 140 h single speaker dataset, as well as VoxCeleb2 (Chung et al., 2018) multi-speaker dataset, has a better performance than the previous works.”
From Audio deepfakes: A survey (2023) · cites this paper as Chung et al., 2018
The cited source says what the claim attributes to it.
In the citing paper
“Meanwhile, the emergence of large-scale VSA datasets [28, 29, 30, 31, 32] promoted the further development of deep learning based VSA research.”
From Deep learning for visual speech analysis: A survey (2024) · cites this paper as [30]
In the citing paper
“Recently, several end-to-end deep speaker recognition models have been devised [169], achieving better performance than i-vector baselines.”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [169]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
(2016) · Cited by 31,590
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
Self-citationDimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Learning a Similarity Metric Discriminatively, with Application to Face Verification
Chopra, S., Hadsell, R., & LeCun, Y. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.202 · Cited by 4,036
Front-End Factor Analysis for Speaker Verification
Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2064307 · Cited by 3,549
Research works printed but not linked: 5
- [7][7] A. Nagrani, J. S. Chung, and A. Zisserman, 'VoxCeleb: a largescale speaker identification dataset,' in INTERSPEECH , 2017. -
- [12][12] A. Ephrat, I. Mosseri, O. Lang, T. Dekel, K. Wilson, A. Hassidim, W. T. Freeman, and M. Rubinstein, 'Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation,' arXiv preprint arXiv:1804.03619 , 2018. - · arXiv
- [32][32] J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, and D. S. Pallett, 'DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1,' NASA STI/Recon technical report , vol. 93, 1993. -
- [33][33] W. M. Fisher, G. R. Doddington, and K. M. Goudie-Marshall, 'The DARPA speech recognition research database: specifications and status,' in Proc. DARPA Workshop on speech recognition , 1986, pp. 93-99. -
- [36][36] J. S. Chung and A. Zisserman, 'Lip reading in profile,' in Proc. BMVC. , 2017. -
Cited by
Items 1,001–1,010 of 1,010
Segment Aggregation for Short Utterances Speaker Verification Using Raw Waveforms
Kim, S.-B., Jung, J.-W., Shim, H.-J., Kim, J.-H., & Yu, H.-J. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1564 · Cited by 9
Why talk to people when you can talk to robots? Far-field speaker identification in the wild
Humblot-Renaux, G., Li, C., & Chrysostomou, D. (2021) · IEEE RO-MAN · doi:10.1109/ro-man50785.2021.9515482 · Cited by 7
Anchor voiceprint recognition in live streaming via RawNet-SA and gated recurrent unit
Yao, J., Zhang, J., Li, J., & Li, Z. (2021) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-021-00234-3 · Cited by 7
Speech synthesis with face embeddings
Wu, X., Ji, S., Wang, J., & Guo, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03227-7 · Cited by 8
Li, Y., Parsan, A., Wang, B., Dong, P., Yao, S., & Qin, R. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105597 · Cited by 7
Emotionally Controllable Talking Face Generation from an Arbitrary Emotional Portrait
Zhao, Z., Zhang, Y., Wu, T., Guo, H., & Li, Y. (2022) · Applied Sciences · doi:10.3390/app122412852 · Cited by 7
Attentional multi-feature fusion for spoofing-aware speaker verification
Shen, Q., Guo, M., Huang, Y., & Ma, J. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10112-w · Cited by 5
AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations
Cai, Z., Kuckreja, K., Ghosh, S., Chuchra, A., Khan, M. H., Tariq, U., Gedeon, T., & Dhall, A. (2025) · Proceedings of the 33rd ACM International Conference on Multimedia · doi:10.1145/3746027.3761979 · Cited by 4
Anshul, A., Gopal, S., Rajan, D., & Chng, E. S. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01283 · Cited by 1
Joint Audio and Speech Understanding
Gong, Y., Liu, A. H., Luo, H., Karlinsky, L., & Glass, J. (2023) · arXiv · doi:10.48550/arxiv.2309.14405 · Cited by 67
“3k 26k 83k LibriTTS [25] x x x - 22k 167k 418k VoxCeleb2 [26] x x x x - 107k 194k 926k MOSEI [24] x x x - 18k 554k 355k Sum 151k 941k 1,784k”
BackgroundMethodInfluential
Metadata
- Authors
- Chung, J. S., Nagrani, A., & Zisserman, A.
- Affiliations
- University of Oxford (GB)
- Venue
- Interspeech 2018
- Publisher
- ISCA
- Published
- 2018-09-02
- Pages
- 1086-1090
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2808631503
- Cited by
- 2,256
- References
- 42
- Citations by year
- 2026: 167 · 2025: 298 · 2024: 315 · 2023: 352 · 2022: 346 · 2021: 337 · 2020: 293 · 2019: 139 · 2018: 9
- FWCI
- 79.44
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EP/M013774/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- speaker recognition, VoxCeleb2, speaker identification, noisy speech, convolutional neural networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.