VoxCeleb: A Large-Scale Speaker Identification Dataset
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index; none of the 16 sources its claims cite is checked for support yet.
Abstract
Most existing datasets for speaker identification contain samples obtained under quite constrained conditions, and are usually hand-annotated, hence limited in size. The goal of this paper is to generate a large scale text-independent speaker identification dataset collected 'in the wild'. We make two contributions. First, we propose a fully automated pipeline based on computer vision techniques to create the dataset from open-source media. Our pipeline involves obtaining videos from YouTube; performing active speaker verification using a two-stream synchronization Convolutional Neural Network (CNN), and confirming the identity of the speaker using CNN based facial recognition. We use this pipeline to curate VoxCeleb which contains hundreds of thousands of 'real world' utterances for over 1,000 celebrities. Our second contribution is to apply and compare various state of the art speaker identification techniques on our dataset to establish baseline performance. We show that a CNN based architecture obtains the best performance for both identification and verification.
Overview
CoChat Summary
TL;DR
The paper introduces VoxCeleb, a fully automated, large-scale speaker identification dataset built from YouTube videos “in the wild,” with 1,251 celebrities and over 100,000 utterances. It also benchmarks speaker recognition methods and reports that a CNN performs best on both identification and verification.
Key findings
- VoxCeleb contains over 100,000 utterances for 1,251 celebrities; the dataset is gender balanced, with 55% male speakers.
- The automated collection pipeline uses active speaker verification and face verification and was tuned to be highly precise: precision = 1.000 for both stages, with recall = 0.613 for active speaker verification and 0.726 for face verification.
- For speaker identification, the CNN achieves 80.5% top-1 and 92.1% top-5 accuracy, compared with 49.0% / 56.6% for I-vectors + SVM and 60.8% / 75.6% for I-vectors + PLDA + SVM.
- For speaker verification, the best reported result is CNN + Embedding with C min det = 0.71 and EER = 7.8%, better than I-vectors + PLDA (0.73, 8.8%) and GMM-UBM (0.80, 15.0%).
Methods
- Built VoxCeleb from YouTube videos using a fully automated multi-stage pipeline: candidate POI list, video download, face tracking, active speaker verification via SyncNet, and face verification via VGG Face CNN.
- Dataset scale/statistics reported: 1,251 POIs, 690 male POIs, 36 / 18 / 8 videos per POI (max/avg/min), 250 / 123 / 45 utterances per POI (max/avg/min), and 145.0 / 8.2 / 4.0 s utterance length (max/avg/min).
- Trained and evaluated a CNN on spectrograms with minimal preprocessing; identification used a 1,251-way classification setup, while verification compared I-vectors/PLDA, GMM-UBM, and CNN embedding approaches.
Limitations
- The paper states that the pipeline is designed to be conservative, and that this means “a lot of the downloaded videos” are discarded to reduce label errors.
- The paper notes that the collection starts from a list of 2,622 identities from VGG Face and uses YouTube search with “interview” appended, which is an evident source of selection bias toward publicly available, interview-like media.
- The dataset is described as coming from open-source media / YouTube, so it is limited to speakers and contexts available there; this is evident from the text, though not stated as a formal limitation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 12 Not checked · 37 Own results and interpretations
In the paper
“| Face verification | [30] | 1.000 | 0.726 |”
What the sources say
- Not checked yetcites [30] [30] O. M. Parkhi, A. Vedaldi, and A. Zisserman, 'Deep face recognition,' in Proceedings of the British Machine Vision Conference , 2015. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Unlike the SITW dataset, both audio and video for each speaker is released.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“| Active speaker verification | [31] | 1.000 | 0.613 |”
What the sources say
- Not checked yetcites [31] [31] P. Chakravarty and T. Tuytelaars, 'Cross-modal supervision for learning active speaker detection in video,' arXiv preprint arXiv:1603.08907 , 2016. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“reduces the number of parameters from 319M in VGG-M to 67M in our network”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“| # of videos per POI | 36 / 18 / 8 |”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
15 more claims
Create a free account to see all 50 claims and to verify the 16 references still open.
- Probably not a substantial claim. 9
- It may state two separate claims as one. 23
- The quote only partly states this claim. 5
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
“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 [31]
In the citing paper
“Although it is mainly built for speaker identification, it also can be used for VSG.”
From Deep learning for visual speech analysis: A survey (2024) · cites this paper as [31]
In the citing paper
“It contains over 100k utterances from 1,251 celebrities.”
From Deep learning for visual speech analysis: A survey (2024) · cites this paper as [31]
In the citing paper
“VoxCeleb1 [31] is a large-scale text-independent audio-visual dataset collected from open-source YouTube media.”
From Deep learning for visual speech analysis: A survey (2024) · cites this paper as [31]
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
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“The network is trained using batch normalisation [40] and all hyper-parameters (e.”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
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
One millisecond face alignment with an ensemble of regression trees
Kazemi, V., & Sullivan, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.241 · Cited by 2,831 · cited 1×
“Facial landmark positions are detected for each face detection using the regression tree based method of [33].”
MethodCNN architectures for large-scale audio classification
Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., et al. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952132 · Cited by 2,023
MatConvNet - Convolutional Neural Networks for MATLAB
Vedaldi, A., & Lenc, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.4564 · Cited by 578 · cited 1×
“Our implementation is based on the deep learning toolbox MatConvNet [39] and trained on a NVIDIA TITAN X GPU.”
MethodCNN Architectures for Large-Scale Audio ClassificationPreprint
Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.09430 · Cited by 217 · cited 1×
“This has led to a very recent shift from hand-crafted features to the domain of deep CNNs which can be applied to higher dimensional inputs [13, 14] and for speaker iden-tification [15].”
BackgroundCross-Modal Supervision for Learning Active Speaker Detection in Video
Chakravarty, P., & Tuytelaars, T. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46454-1_18 · Cited by 70 · cited 2×
“Precision-recall curves for both tasks on their respective benchmark datasets [30, 31] are shown in Figure 1 right, and the values at the operating point are given in Table 3.”
BackgroundCross-modal Supervision for Learning Active Speaker Detection in VideoPreprint
Chakravarty, P., & Tuytelaars, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08907 · Cited by 1 · cited 2×
“Precision-recall curves for both tasks on their respective benchmark datasets [30, 31] are shown in Figure 1 right, and the values at the operating point are given in Table 3.”
Background
Research works printed but not linked: 28
- [2][2] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'ImageNet classification with deep convolutional neural networks,' in Advances in Neural Information Processing Systems , pp. 1106-1114, 2012. -
- [5][5] M. McLaren, L. Ferrer, D. Castan, and A. Lawson, 'The speakers in the wild (SITW) speaker recognition database,' INTERSPEECH , vol. 2016, 2016. -
- [6][6] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, S. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. Berg, and F. Li, 'Imagenet large scale visual recognition challenge,' International Journal of Computer Vision , 2015. -
- [7][7] D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, 'Speaker verification using adapted gaussian mixture models,' Digital signal processing , vol. 10, no. 1-3, pp. 19-41, 2000. -
- [8][8] D. A. Reynolds and R. C. Rose, 'Robust text-independent speaker identification using gaussian mixture speaker models,' IEEE transactions on speech and audio processing , vol. 3, no. 1, pp. 7283, 1995. -
- [10][10] N. Dehak, P. J. Kenny, R. Dehak, P. Dumouchel, and P. Ouellet, 'Front-end factor analysis for speaker verification,' IEEE Transactions on Audio, Speech, and Language Processing , vol. 19, no. 4, pp. 788-798, 2011. -
- [11][11] U. H. Yapanel, X. Zhang, and J. H. Hansen, 'High performance digit recognition in real car environments.,' in INTERSPEECH , 2002. -
- [12][12] J. H. Hansen, R. Sarikaya, U. H. Yapanel, and B. L. Pellom, 'Robust speech recognition in noise: an evaluation using the spine corpus.,' in INTERSPEECH , pp. 905-908, 2001. -
- [13][13] T. N. Sainath, R. J. Weiss, A. W. Senior, K. W. Wilson, and O. Vinyals, 'Learning the speech front-end with raw waveform CLDNNs,' in INTERSPEECH , pp. 1-5, 2015. -
- [15][15] Y. Lukic, C. Vogt, O. D¨ urr, and T. Stadelmann, 'Speaker identification and clustering using convolutional neural networks,' in IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP) , pp. 1-6, IEEE, 2016. -
- [16][16] D. van der Vloed, J. Bouten, and D. A. van Leeuwen, 'NFIFRITS: a forensic speaker recognition database and some first experiments,' in The Speaker and Language Recognition Workshop , 2014. -
- [17][17] J. Hennebert, H. Melin, D. Petrovska, and D. Genoud, 'POLYCOST: a telephone-speech database for speaker recognition,' Speech communication , vol. 31, no. 2, pp. 265-270, 2000. -
- [18][18] J. B. Millar, J. P. Vonwiller, J. M. Harrington, and P. J. Dermody, 'The Australian national database of spoken language,' in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , vol. 1, pp. I-97, IEEE, 1994. -
- [19][19] 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. -
- [21][21] R. Woo, A. Park, and T. J. Hazen, 'The MIT Mobile Device Speaker Verification Corpus: Data collection and preliminary experiments,' The Speaker and Language Recognition Workshop , 2006. -
- [23][23] A. Janin, D. Baron, J. Edwards, D. Ellis, D. Gelbart, N. Morgan, B. Peskin, T. Pfau, E. Shriberg, A. Stolcke, et al. , 'The ICSI meeting corpus,' in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , vol. 1, IEEE, 2003. -
- [24][24] I. McCowan, J. Carletta, W. Kraaij, S. Ashby, S. Bourban, M. Flynn, M. Guillemot, T. Hain, J. Kadlec, V. Karaiskos, et al. , 'The AMI meeting corpus,' in International Conference on Methods and Techniques in Behavioral Research , vol. 88, 2005. -
- [25][25] P. Bell, M. J. Gales, T. Hain, J. Kilgour, P. Lanchantin, X. Liu, A. McParland, S. Renals, O. Saz, M. Wester, et al. , 'The MGB challenge: Evaluating multi-genre broadcast media recognition,' in IEEE Workshop on Automatic Speech Recognition and Understanding , pp. 687-693, IEEE, 2015. -
- [27][27] J. J. Godfrey, E. C. Holliman, and J. McDaniel, 'Switchboard: Telephone speech corpus for research and development,' in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , vol. 1, pp. 517-520, IEEE, 1992. -
- [28][28] 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 , pp. 93-99, 1986. -
- [30][30] O. M. Parkhi, A. Vedaldi, and A. Zisserman, 'Deep face recognition,' in Proceedings of the British Machine Vision Conference , 2015. -
- [32][32] D. E. King, 'Dlib-ml: A machine learning toolkit,' The Journal of Machine Learning Research , vol. 10, pp. 1755-1758, 2009. -
- [34][34] J. S. Chung and A. Zisserman, 'Lip reading in the wild,' in Proceedings of the Asian Conference on Computer Vision , 2016. -
- [35][35] M. Everingham, J. Sivic, and A. Zisserman, 'Taking the bite out of automatic naming of characters in TV video,' Image and Vision Computing , vol. 27, no. 5, 2009. -
- [36][36] J. S. Chung and A. Zisserman, 'Out of time: automated lip sync in the wild,' in Workshop on Multi-view Lip-reading, ACCV , 2016. -
- [37][37] K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman, 'Return of the devil in the details: Delving deep into convolutional nets,' in Proceedings of the British Machine Vision Conference , 2014. -
- [38][38] S. Chopra, R. Hadsell, and Y. LeCun, 'Learning a similarity metric discriminatively, with application to face verification,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , vol. 1, pp. 539-546, IEEE, 2005. -
- [41][41] S. Ioffe, 'Probabilistic linear discriminant analysis,' in Proceedings of the European Conference on Computer Vision , pp. 531542, Springer, 2006.
Cited by
Items 401–500 of 1,008
Gaussian-constrained Training for Speaker Verification
Li, L., Tang, Z., Shi, Y., & Wang, D. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683245 · Cited by 25
Robust Speaker Recognition Using Unsupervised Adversarial Invariance
Peri, R., Pal, M., Jati, A., Somandepalli, K., & Narayanan, S. S. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054601 · Cited by 26
Vo, S. A., Scanlan, J. D., Turner, P. A., & Ollington, R. (2020) · Food Control · doi:10.1016/j.foodcont.2020.107419 · Cited by 26
Attention Back-End for Automatic Speaker Verification with Multiple Enrollment Utterances
Zeng, C., Wang, X., Cooper, E., Miao, X., & Yamagishi, J. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746688 · Cited by 36
“Although the main advantage of the proposed method is that multiple enrollment utterances can be used, we first confirmed the performance of the proposed back-end using a single enrollment case on the VoxCeleb dataset.”
MethodInfluentialLanguage-Independent Speaker Anonymization Approach Using Self-Supervised Pre-Trained Models
Miao, X., Wang, X., Cooper, E., Yamagishi, J., & Tomashenko, N. (2022) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2022-39 · Cited by 46
Duration Controllable Voice Conversion via Phoneme-Based Information Bottleneck
Lee, S.-H., Noh, H.-R., Nam, W.-J., & Lee, S. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3156757 · Cited by 33
HR-Net: A Landmark Based High Realistic Face Reenactment Network
Ren, Q., Lu, Z., Wu, H., Zhang, J., & Dong, Z. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3268062 · Cited by 30
“B. Compared to SOTA 1) Method: In this study, we comprehensively evaluated our proposed method by comparing it against five state-of-the-art methods on both the RaFD [46] and VoxCeleb-1 [47] datasets.”
BackgroundMethodGul, S., & Khan, M. S. (2023) · IEEE Access · doi:10.1109/access.2023.3344813 · Cited by 31
The VoxCeleb Speaker Recognition Challenge: A Retrospective
Huh, J., Chung, J. S., Nagrani, A., Brown, A., Jung, J.-W., Garcia-Romero, D., & Zisserman, A. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3444456 · Cited by 43
“Participants were allowed to use any data to train their models except the test data.”
MethodSelf-citationInteractive Face Video Coding: A Generative Compression Framework
Chen, B., Wang, Z., Li, B., Wang, S., Wang, S., & Ye, Y. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3563762 · Cited by 36
“The 50 testing sequences selected and pre-processed from VoxCeleb testing dataset [98]. texture loss L tex and pixel loss L pixel .”
End-to-End Multi-Speaker Speech Recognition Using Speaker Embeddings and Transfer Learning
Denisov, P., & Vu, N. T. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1130 · Cited by 31
Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?
Cooper, E., Lai, C.-I., Yasuda, Y., & Yamagishi, J. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1229 · Cited by 29
“[36] J. S. Chung, A. Nagrani, and A. Zisserman, “VoxCeleb2: Deep speaker recognition,” arXiv preprint arXiv:1806.05622, 2018.”
MethodInfluentialSmartphone Multi-modal Biometric Authentication: Database and EvaluationPreprint
Ramachandra, R., Stokkenes, M., Mohammadi, A., Venkatesh, S. K., Raja, K. B., Wasnik, P., Poiret, E., Marcel, S., & Busch, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02487 · Cited by 27
“The DRN model is one of the state-of-the-art systems on the Voxceleb 1 database [31] evaluations achieving 4.”
ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings
Thienpondt, J., & Demuynck, K. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389750 · Cited by 65
“In recent years, the field has gained significant performance improvements due to the availability of large, labeled datasets [1, 2] and the development of specialized neural network architectures [3, 4].”
BackgroundNoise Robust Speaker Recognition Based on Adaptive Frame Weighting in GMM for i-Vector Extraction
Zhang, X., Zou, X., Sun, M., Zheng, T. F., Jia, C., & Wang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2901812 · Cited by 25
“…with realworld noise, consisting of background chatter, laughter, overlapping speech, room acoustics, and there is a range in the quality of recording equipment and channel noise [33] VoxCeleb2 contains over 1 million utterances for over 6,000 celebrities, extracted from videos uploaded to YouTube.”
BackgroundLearning Discriminative Joint Embeddings for Efficient Face and Voice Association
Wang, R., Liu, X., Cheung, Y., Cheng, K., Wang, N., & Fan, W. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401302 · Cited by 26
“The popular VoxCeleb [12] dataset is selected for facevoice association.”
MethodPhoneme-Unit-Specific Time-Delay Neural Network for Speaker Verification
Chen, X., & Bao, C. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3065202 · Cited by 26
“Our experiments are carried out on the Fisher [45], NIST SRE10 [46], and VoxCeleb [47], [48] datasets.”
BackgroundMethodOne-shot Face Reenactment Using Appearance Adaptive Normalization
Yao, G., Yuan, Y., Shao, T., Li, S., Liu, S., Liu, Y., Wang, M., & Zhou, K. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i4.16427 · Cited by 29
Voxceleb Enrichment for Age and Gender Recognition
Hechmi, K., Trọng, T. N., Hautamäki, V., & Kinnunen, T. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688085 · Cited by 27
Extended U-Net for Speaker Verification in Noisy Environments
Kim, J.-H., Heo, J., Shim, H.-J., & Yu, H.-J. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-155 · Cited by 28
U-WeAr: User Recognition on Wearable Devices through Arm Gesture
Bianco, S., Napoletano, P., Raimondi, A., & Rima, M. (2022) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2022.3170829 · Cited by 27
Kang, W. H., Alam, J., & Fathan, A. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3196562 · Cited by 29
“The evaluation was performed according to the original VoxCeleb1 trial list (VoxCeleb1-O) [29], which consists of 4,874 utterances spoken by 40 speakers.”
MethodComputational Intelligence-Based Stuttering Detection: A Systematic Review
Alnashwan, R., Alhakbani, N., Al-Nafjan, A., Almudhi, A., & Al-Nuwaiser, W. M. (2023) · Diagnostics · doi:10.3390/diagnostics13233537 · Cited by 29
“In the literature, researchers have applied various datasets, including University College London’s Archive of Stuttered Speech ( UCLASS ) [11], SEP-28k [12], FluencyBank [13], and LibriStutter [14], and have also used resources like VoxCeleb [15] (see Table 1).”
MethodRochow, A., Schwarz, M., & Behnke, S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00737 · Cited by 43
“Cross-reenactment comparison with absolute motion transfer on the VoxCeleb test set [27].”
BackgroundMethodInfluentialCharacterizing Performance of Speaker Diarization Systems on Far-Field Speech Using Standard Methods
Maciejewski, M., Snyder, D., Manohar, V., Dehak, N., & Khudanpur, S. P. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461546 · Cited by 25
Perfect Match: Self-Supervised Embeddings for Cross-Modal Retrieval
Chung, S.-W., Chung, J. S., & Kang, H.-G. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987720 · Cited by 30
“Dataset: For training the models, we use the same subset of the VoxCeleb1 [48] dataset that is used by [26].”
MethodSelf-citationThe DKU-DukeECE Systems for VoxCeleb Speaker Recognition Challenge 2020Preprint
Wang, W., Cai, D., Qin, X., & Li, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12731 · Cited by 49
“For speaker embedding training, we use Voxceleb1&2 [20] for speaker embedding training.”
MethodSentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis
Fan, Q., Han, J., He, Y., Zheng, T., & Zheng, G. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.821 · Cited by 35
AdvReverb: Rethinking the Stealthiness of Audio Adversarial Examples to Human Perception
Chen, M., Lü, L., Yu, J., Ba, Z., Lin, F., & Ren, K. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3345639 · Cited by 28
“2) Dataset Statistics: As shown in Table IV, we employ samples in Google Speech Command [33], VoxCeleb1 [34], and LibriSpeech [35] as speech carrier.”
MethodInfluentialSAFA: Structure Aware Face Animation
Wang, Q., Zhang, L., & Li, B. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00077 · Cited by 35
FreeStyleGAN: free-view editable portrait rendering with the camera manifold
Leimkühler, T., & Drettakis, G. (2021) · ACM Transactions on Graphics · doi:10.1145/3478513.3480538 · Cited by 34
SVTS: Scalable Video-to-Speech Synthesis
Mira, R., Haliassos, A., Petridis, S., Schuller, B. W., & Pantić, M. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10770 · Cited by 51
$$\text {Face2Face}^\rho $$: Real-Time High-Resolution One-Shot Face Reenactment
Yang, K., Chen, K., Guo, D., Zhang, S., Guo, Y.-C., & Zhang, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19778-9_4 · Cited by 53
“We train Face2Face ρ on the VoxCeleb dataset [26], which contains over 20k video sequences of different actors.”
MethodKim, T., Chung, C., Kim, Y., Park, S., Kim, K., & Choo, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19790-1_12 · Cited by 37
Free-HeadGAN: Neural Talking Head Synthesis With Explicit Gaze Control
Doukas, M. C., Ververas, E., Sharmanska, V., & Zafeiriou, S. P. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3253243 · Cited by 33
“TABLE 2: Numerical comparison with state-of-the-art methods on the tasks of self-reenactment (same-identity reconstruction) and reenactment (cross-identity motion transfer) for VoxCeleb [59] test set.”
BackgroundMethodInfluentialSerafini, L., Cornell, S., Morrone, G., Zovato, E., Brutti, A., & Squartini, S. (2023) · Computer Speech & Language · doi:10.1016/j.csl.2023.101534 · Cited by 28
“This model is trained for a speaker recognition task as the original x-vector architecture [32] on a large amount of data consisting of VoxCeleb1 (323 h, 1 211 speakers) [98], VoxCeleb2 (2 290 h, 5 994 speakers) [99], CNCELEB (264 h, 973 speakers) [100], NIST-SRE 2004-2010 (3805 h, 4 254 speakers), Switchboard (SWBD)…”
Saritha, B., Laskar, M. A., Kirupakaran, A. M., Laskar, R. H., & Choudhury, M. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109100 · Cited by 24
DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads
Kim, S., Kwon, H., Song, J., Jo, J., Chen, Y., Lai, L., & Chandra, V. (2023) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3623278.3624753 · Cited by 39
“For AR_Social , we create speaker identifying ML pipeline based on [23] and use its VGG-based model for active speaker verification.”
MethodSubjective Evaluation of Media Consumer Vulnerability to Fake Audiovisual Content
Khodabakhsh, A., Ramachandra, R., & Busch, C. (2019) · 2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2019.8743316 · Cited by 22
“For the control set, 24 videos were randomly selected from the VoxCeleb [9] dataset after filtering those with regards to the same duration and quality criteria.”
MethodAdaptive Blind Audio Source Extraction Supervised By Dominant Speaker Identification Using X-Vectors
Janský, J., Málek, J., Čmejla, J., Kounovský, T., Koldovský, Z., & Žďánský, J. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054693 · Cited by 23
“The data originate in the development part of the Voxceleb database [18].”
MethodHow Far Are We from Robust Voice Conversion: A Survey
Huang, T.-H., Lin, J.-H., & Lee, H.-Y. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383498 · Cited by 39
Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning
Sang, M., & Hansen, J. H. L. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-892 · Cited by 27
Rathipriya, N., & Maheswari, N. (2024) · IEEE Access · doi:10.1109/access.2024.3463969 · Cited by 26
Favaro, A., Butala, A., Thebaud, T., Villalba, J., Dehak, N., & Moro-Velázquez, L. (2024) · npj Parkinson s Disease · doi:10.1038/s41531-024-00817-9 · Cited by 35
“In this work, x-vectors were extracted from a model trained on both Voxceleb1 (English only) 80 and Voxceleb2 (multi-lingual) 81 on a speaker-veri fi cation task.”
MethodSynchronous Multi-Modal Semantic Communication System With Packet-Level Coding
Tian, Y., Ying, J., Qin, Z., Jin, Y., & Tao, X. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3534995 · Cited by 29
“A. Simulation Configuration 1) Datasets: For training and testing video semantic coding, packet coding and image generator, we use the VoxCeleb dataset [40] as the transmission source.”
Heo, H.-S., Jung, J.-W., Yang, I.-H., Yoon, S.-H., Shim, H.-J., & Yu, H.-J. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1986 · Cited by 22
Personalized voice activated grasping system for a robotic exoskeleton glove
Guo, Y., Xu, W., Pradhan, S., Bravo, C. J., & Ben‐Tzvi, P. (2022) · Mechatronics · doi:10.1016/j.mechatronics.2022.102745 · Cited by 22
Voting for the Right Answer: Adversarial Defense for Speaker Verification
Wu, H., Zhang, Y., Wu, Z., Wang, D., & Lee, H.-Y. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1452 · Cited by 30
Pretext Tasks Selection for Multitask Self-Supervised Audio Representation Learning
Zaiem, S., Parcollet, T., Essid, S., & Heba, A. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3195430 · Cited by 31
Zheng, Q., Chen, Z., Liu, H., Lu, Y., Li, J., & Liu, T. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119511 · Cited by 24
Pushing the Limits of Self-Supervised Speaker Verification using Regularized Distillation Framework
Chen, Y., Zheng, S., Wang, H., Cheng, L., & Chen, Q. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096915 · Cited by 22
Defend Data Poisoning Attacks on Voice Authentication
Li, K., Baird, C., & Lin, D. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3289446 · Cited by 32
“the LibriSpeech 1 [75] and VoxCeleb [76], [77], [78] datasets.”
MethodA Federated Attention-Based Multimodal Biometric Recognition Approach in IoT
Lin, L., Zhao, Y., Meng, J., & Zhao, Q. (2023) · Sensors · doi:10.3390/s23136006 · Cited by 24
“In our study, the VoxCeleb1 and VoxCeleb2 datasets [31,32] were utilized to train and test our AMBR model, which includes large-scale audio-visual data comprising short speech segments extracted from interview videos on YouTube.”
DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
Hong, F.-T., Shen, L., & Xu, D. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3339964 · Cited by 43
“Duringthetrainingphase, weinitiallytrainourenhanceduncertainty-guidedfacialdepth network using consecutive frames from VoxCeleb1 videos and maintain it fixed throughout the training of the entire deep generation framework.”
BackgroundInfluentialMamun, K. A., Nabid, R. A., Pranto, S. I., Lamim, S. M., Rahman, M. M., Mahammed, N., Huda, M. N., Sarker, F., & Khan, R. R. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108923 · Cited by 28
VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior
Sun, X., Zhang, L., Zhu, H., Zhang, P., Zhang, B., Ji, X., Zhou, K., Gao, D., Bo, L., & Cao, X. (2025) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv66043.2025.00071 · Cited by 65
“We train our model with the HDTF [36] dataset and VoxCeleb [15] dataset.”
MethodSpeaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors
Maghsoodi, N., Sameti, H., Zeinali, H., & Stafylakis, T. (2019) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2019.2928143 · Cited by 23
“The embedding extractor is implemented using the standard Kaldi recipe, and it is trained on VoxCeleb 1 and 2 (containing more that 7K speakers) [39].”
MethodSpeaker Verification by Partial AUC Optimization With Mahalanobis Distance Metric Learning
Bai, Z., Zhang, X.-L., & Chen, J. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.2990275 · Cited by 23
“VoxCeleb consists of VoxCeleb1 [52] and VoxCeleb2 [53], which contains over 1 million recordings from 7,363 celebrities.”
BackgroundA network model of speaker identification with new feature extraction methods and asymmetric BLSTM
Wang, X., Xue, F., Wang, W., & Liu, A. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.04.041 · Cited by 22
Metric Learning for Keyword Spotting
Huh, J., Lee, M., Heo, H.-S., Mun, S., & Chung, J. S. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383571 · Cited by 24
“Metric learning objectives such as the contrastive loss [18, 19] and triplet loss [20, 21] have been used widely in both face recognition [22, 23] and speaker verification [24, 25].”
MethodSelf-citationYounis, H. A., Ruhaiyem, N. I. R., Badr, A. A., Abdul-Hassan, A. K., Alfadli, I. M., Binjumah, W. M., Altuwaijri, E. A., & Nasser, M. (2023) · Processes · doi:10.3390/pr11051488 · Cited by 21
Narrowing Domain Gaps With Bridging Samples for Generalized Face Forgery Detection
Yu, Y., Ni, R., Yang, S., Zhao, Y., & Kot, A. C. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3310341 · Cited by 28
“Moreover, 10000 real faces are collected from VoxCeleb1 [64], and corresponding 10000 forgery faces generated by DGN [7].”
MethodSpoofCeleb: Speech Deepfake Detection and SASV in the Wild
Jung, J.-W., Wu, Y., Wang, X., Kim, J.-H., Maiti, S., Matsunaga, Y., Shim, H.-J., Tian, J., Evans, N., Chung, J. S., et al. (2025) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2025.3529377 · Cited by 80
“To this end, we introduce SpoofCeleb, a dataset built upon VoxCeleb1 [14], a widely used ASV dataset consisting of the voices of 1 , 251 celebrities recorded under real-world conditions.”
Self-citationCross-Modal Knowledge Distillation With Multi-Stage Adaptive Feature Fusion for Speech Separation
Fan, C., Xiang, W., Tao, J., Yi, J., & Lv, Z. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3533359 · Cited by 39
“Notably, there is no overlap between the identities included in VoxCeleb2 and those in VoxCeleb1 [80] datasets.”
Huang, C.-L. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003938 · Cited by 22
“In addition to feed-forward neural networks, the convolutional neural networks based speaker recognition was proposed in 2017 [9].”
BackgroundMethodHybrid Network For End-To-End Text-Independent Speaker Identification
Ghezaiel, W., Brun, L., & Lézoray, O. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413293 · Cited by 24
“Some works have proposed to directly feed networks with spectrogram bins [23], [24] or even with raw waveforms [25], [26].”
BackgroundSang, M., Xia, W., & Hansen, J. H. L. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413403 · Cited by 27
“We use the development set of Voxceleb1 and Voxceleb2 (refer to as Vox1-dev and Vox2-dev) which were collected “in the wild” [25, 26] as our source domain data.”
MethodLook Who’s Talking: Active Speaker Detection in the Wild
Kim, Y. J., Heo, H.-S., Choe, S., Chung, S.-W., Kwon, Y., Lee, B., Kwon, Y., & Chung, J. S. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-2041 · Cited by 38
Self-citationImperceptible black-box waveform-level adversarial attack towards automatic speaker recognition
Zhang, X., Zhang, X., Sun, M., Zou, X., Chen, K., & Yu, N. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00782-x · Cited by 26
“Experimental evaluation of the proposed methods is conducted on the commonly used data sets for speaker recognition, say VoxCeleb1 [41], VoxCeleb2 [42] and LibriSpeech [43].”
MethodSpeaker identification and localization using shuffled MFCC features and deep learning
Barhoush, M., Hallawa, A., & Schmeink, A. (2023) · International Journal of Speech Technology · doi:10.1007/s10772-023-10023-2 · Cited by 23
“In addition, machine learning helped achieving best performances in speaker identification applications (Ashar et al., 2020; An et al., 2019; Zhang et al., 2019; Nagrani et al., 2017; Ye et al., 2021; Ravanelli et al., 2018; Ghezaiel et al., 2020; Barhoush et al., 2021).”
BackgroundMethodStyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment
Bounareli, S., Tzelepis, C., Argyriou, V., Patras, I., & Tzimiropoulos, G. (2023) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg57933.2023.10042744 · Cited by 31
“Recently, the works of [16] and [19] propose the use of 3D shape models to transfer the facial motion, and in [15], Bounareli et al. introduce a novel approach on neural face reenactment by finding directions in the latent space of a pretrained StyleGAN2 on the VoxCeleb dataset [21], that control the facial attributes…”
BackgroundInfluentialImproving Transformer-Based Networks with Locality for Automatic Speaker Verification
Sang, M., Zhao, Y., Liu, G., Hansen, J. H. L., & Wu, J. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096333 · Cited by 27
Cross-Modal Distillation for Speaker Recognition
Jin, Y., Hu, G., Chen, H., Miao, D., Hu, L., & Zhao, C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26525 · Cited by 30
“All rights reserved. deep learning, neural networks (Nagrani, Chung, and Zisserman 2017; Snyder et al. 2018; Okabe, Koshinaka, and Shinoda 2018) started to become the mainstream and achieved promising progress.”
BackgroundMethodInfluentialAniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding
Liu, T., Chen, F., Fan, S., Du, C., Chen, Q., Chen, X., & Yu, K. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681198 · Cited by 88
“Weutilizes threedatasets:VoxCeleb[30],HDTF[59],andVFHQ[52].”
MethodSoleymani, S., Dabouei, A., Iranmanesh, S. M., Kazemi, H., Dawson, J. M., & Nasrabadi, N. M. (2018) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2018.8698585 · Cited by 23
A Simplified Speaker Recognition System Based on FPGA Platform
Xu, J., Li, S., Jiang, J., & Dou, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2944644 · Cited by 21
“Moreover, CNNs or RNNs can achieve high accuracy when handing large-scale real datasets, such as VoxCeleb1, which is unavailable in traditional algorithms.”
MethodInfluentialNISP: A Multi-lingual Multi-accent Dataset for Speaker Profiling
Kalluri, S. B., Vijayasenan, D., Ganapathy, S., Ragesh Rajan, M., & Krishnan, P. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414349 · Cited by 21
Thienpondt, J., Desplanques, B., & Demuynck, K. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2662 · Cited by 27
Double Multi-Head Attention for Speaker Verification
India, M., Safari, P., & Hernando, J. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414877 · Cited by 23
“The proposed system(1) in this work has been assessed by VoxCeleb dataset [28, 7].”
MethodSang, M., Xia, W., & Hansen, J. H. L. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2868 · Cited by 21
Learnable MFCCs for Speaker Verification
Liu, X., Sahidullah, M., & Kinnunen, T. (2021) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas51556.2021.9401593 · Cited by 26
Federated Learning for Privacy-Preserving Speaker Recognition
Woubie, A., & Bäckström, T. (2021) · IEEE Access · doi:10.1109/access.2021.3124029 · Cited by 23
“The proposed speaker verification system has been carried out on the VoxCeleb-1 database [25].”
MethodFrom Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from SpeechPreprint
Choi, H.-S., Park, C., & Lee, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05830 · Cited by 26
“Oh et al. (2019) proposed a similar work called speech2face.”
USTC-NELSLIP System Description for DIHARD-III ChallengePreprint
Wang, Y., He, M., Niu, S., Sun, L., Gao, T., Fang, X., Pan, J., Du, J., & Lee, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.10661 · Cited by 28
“For xvector extraction, the training data was drawn from VoxCeleb 1 [8] and 2 [9] with data augmentation, amounting to 6 million utterances from 7146 speakers.”
MethodAudio-Driven Facial Animation with Deep Learning: A Survey
Jiang, D., Chang, J. M., You, L., Bian, S., Kosk, R., & Maguire, G. (2024) · Information · doi:10.3390/info15110675 · Cited by 38
VAE-Based Regularization for Deep Speaker Embedding
Zhang, Y., Li, L., & Wang, D. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2486 · Cited by 21
SpecAugment Impact on Automatic Speaker Verification System
Faisal, M. Y., & Suyanto, S. (2019) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti48646.2019.9034603 · Cited by 24
“Some other new research also proposed DNNs to work with this problem [10], [11], [12].”
BackgroundMethodInfluentialIntra-Class Variation Reduction of Speaker Representation in Disentanglement Framework
Kwon, Y., Chung, S.-W., & Kang, H.-G. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2075 · Cited by 20
CNN-based Text-independent Automatic Speaker Identification Using Short Utterances
Fasounaki, M., Yüce, E. B., Oncul, S., & İnce, G. (2021) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk52708.2021.9559031 · Cited by 23
Lip as biometric and beyond: a survey
Chowdhury, D. P., Kumari, R., Bakshi, S., Sahoo, M. N., & Das, A. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11613-5 · Cited by 20
Adversarial Sample Detection for Speaker Verification by Neural Vocoders
Wu, H., Hsu, P.-C., Gao, J., Zhang, S., Huang, S., Kang, J., Wu, Z., Meng, H. M. L., & Lee, H.-Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746900 · Cited by 27
“We trained the model on the dev set of VoxCeleb1 [30] for 1000k iterations, which takes around 5 days.”
MethodInfluentialPerson identification based on voice biometric using deep neural network
Al-Shakarchy, N. D., Obayes, H. K., & Abdullah, Z. N. (2022) · International Journal of Information Technology · doi:10.1007/s41870-022-01142-1 · Cited by 29
“VoxCeleb1 contains more than 100,000 utterances for 1,251 celebrities, taken from videos found on You-Tube [22].”
BackgroundPeng, J., Stafylakis, T., Gu, R., Plchot, O., Mošner, L., Burget, L., & Černocký, J. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094795 · Cited by 31
“Data-sets: The SV performance is evaluated on the VoxCeleb [4, 5] and CNCeleb [21, 22] The Large model has 24 transformer blocks with 1024-dimensional output resulting in 316M parameters.”
BackgroundMethodSpeech Self-Supervised Representation Benchmarking: Are We Doing it Right?
Zaiem, S., Kemiche, Y., Parcollet, T., Essid, S., & Ravanelli, M. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-1087 · Cited by 49
An Intelligent Infrastructure Toward Large Scale Naturalistic Affective Speech Corpora Collection
Upadhyay, S. G., Chien, W.-S., Su, B.-H., Goncalves, L., Wu, Y.-T., Salman, A. N., Busso, C., & Lee, C.-C. (2023) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii59096.2023.10388175 · Cited by 41
“In the speech, Nagrani’s fully automated pipeline [21] uses computer vision techniques to collect data from”
Significance of chirp MFCC as a feature in speech and audio applications
Joysingh, S. J., Vijayalakshmi, P., & Nagarajan, T. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101713 · Cited by 20
“2) Dataset: Voxceleb1 dataset [34] is used for this task.”
MethodÜlgen, İ. R., Du, Z., Busso, C., & Şişman, B. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447060 · Cited by 36
“In contrast to SER, SV benefits from the availability of sufficient labeled data [6, 7].”
BackgroundVoxblink: A Large Scale Speaker Verification Dataset on Camera
Lin, Y., Qin, X., Zhao, G., Cheng, M., Jiang, N., Wu, H., & Li, M. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446780 · Cited by 39
“VoxCeleb [8, 9] stands out as the most successful as it contains over one million utterances from thousands of speakers.”
BackgroundGenerative Face Video Coding Techniques and Standardization Efforts: A Review
Chen, B., Chen, J., Wang, S., & Yan, Y. (2024) · DCC · doi:10.1109/dcc58796.2024.00018 · Cited by 25
“• For the testing dataset, there are 50 talking face video sequences selected as testing sequences from the VoxCeleb dataset [35].”
MethodDeveloping Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
Lu, K.-H., Chen, Z., Fu, S., Yang, C.-H. H., Balam, J., Ginsburg, B., Wang, Y.-C. F., & Lee, H.-Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889444 · Cited by 61
Metadata
- Authors
- Nagrani, A., Chung, J. S., & Zisserman, A.
- Venue
- Interspeech 2017
- Publisher
- ISCA
- Published
- 2017-08-20
- Pages
- 2616-2620
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2726515241
- Cited by
- 2,210
- References
- 4
- Citations by year
- 2026: 144 · 2025: 280 · 2024: 313 · 2023: 361 · 2022: 330 · 2021: 319 · 2020: 265 · 2019: 151 · 2018: 47
- FWCI
- 56.51
- 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 › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- speaker identification, speaker verification, VoxCeleb, text-independent speaker recognition, automated dataset generation, two-stream CNN, face recognition, YouTube videos
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.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.