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 301–400 of 1,008
S-Vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder
Mary, N. J. M. S., Umesh, S., & Katta, S. V. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3134566 · Cited by 48
“We used two datasets in training our models: VoxCeleb-1 [34] and VoxCeleb-2 [6].”
MethodFusion and Orthogonal Projection for Improved Face-Voice Association
Saeed, M. S., Khan, M. H., Nawaz, S., Yousaf, M. H., & Bue, A. D. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747704 · Cited by 58
End-to-End Active Speaker Detection
Alcázar, J. L., Cordes, M., Zhao, C., & Ghanem, B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19836-6_8 · Cited by 38
iQIYI-VID: A Large Dataset for Multi-modal Person IdentificationPreprint
Liu, Y., Peng, B., Shi, P., Yan, H., Zhou, Y., Han, B., Zheng, Y., Lin, C., Jiang, J., Yin, F., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07548 · Cited by 38
“Speaker recognition falls into two categories, text dependent [41] and text independent [42].”
BackgroundPersonalized PercepNet: Real-Time, Low-Complexity Target Voice Separation and Enhancement
Giri, R., Venkataramani, S., Valin, J.-M., Isik, U., & Krishnaswamy, A. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-694 · Cited by 49
“Following the data filtering technique described in [28], we isolate the clean speech in VoxCeleb2 and VoxCeleb1 and eliminate reverberant clips.”
MethodInfluentialHashmi, A., Shahzad, S. A., Lin, C., Tsao, Y., & Wang, H. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3554477 · Cited by 47
Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model
Brümmer, N., Silnova, A., Burget, L., & Stafylakis, T. (2018) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2018-49 · Cited by 34
Audio-Visual Person Recognition in Multimedia Data From the Iarpa Janus Program
Sell, G., Duh, K., Snyder, D., Etter, D., & Garcia-Romero, D. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462122 · Cited by 35
“Even more recently, the VoxCeleb database [11] was released.”
BackgroundImproved Speech Separation with Time-and-Frequency Cross-Domain Joint Embedding and Clustering
Yang, G.-P., Tuan, C.-I., Lee, H.-Y., & Lee, L.-S. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2181 · Cited by 38
“Substantial effort has been made on this problem, obviously because good solutions to it may lead to good contributions to many downstream tasks such as speech recognition [1], speaker identification [2], and audio classification [3] in noisy environment.”
BackgroundGenerative Adversarial Networks in Human Emotion Synthesis: A Review
Hajarolasvadi, N., Ramírez, M. A., Beccaro, W., & Demirel, H. (2020) · IEEE Access · doi:10.1109/access.2020.3042328 · Cited by 42
Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Nawaz, S., Saeed, M. S., Morerio, P., Mahmood, A., Gallo, I., Yousaf, M. H., & Bue, A. D. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00184 · Cited by 57
“[34] for collecting the proposed dataset.”
InfluentialUniversal Paralinguistic Speech Representations Using self-Supervised Conformers
Shor, J., Jansen, A., Han, W., Park, D., & Zhang, Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747197 · Cited by 61
IdentityMask: Deep Motion Flow Guided Reversible Face Video De-Identification
Wen, Y., Liu, B., Cao, J., Xie, R., Song, L., & Li, Z. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3191982 · Cited by 40
“A. Experimental Setup 1) Dataset: We choose the VoxCeleb dataset [49], which contains 22496 videos extracted from YouTube, to demonstrate the effectiveness of our reversible face video de-identification method.”
MethodMasked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input
Niizumi, D., Takeuchi, D., Ohishi, Y., Harada, N., & Kashino, K. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097236 · Cited by 67
“Tasks include environmental sound classi-fication ESC-50 [29] and UrbanSound8K [30] (US8K), speech-command classification Speech Commands V2 [31] (SPCV2), speaker identification VoxCeleb1 [32] (VC1), language identifi-cation VoxForge [33] (VF), speech emotion recognition CREMA-D [34] (CRM-D), music genre recognition GTZAN…”
BackgroundEnd-To-End Accent Conversion Without Using Native Utterances
Liu, S., Wang, D., Cao, Y., Sun, L., Wu, X., Kang, S., Wu, Z., Liu, X., Su, D., Yu, D., et al. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053797 · Cited by 54
“We use LibriSpeech (train-other-500) [20], VoxCeleb1 [21] and Vox-Celeb2 [22] datasets to train the speaker encoder.”
MethodSpeaker Recognition Using Machine Learning Techniques
Sharma, A. M. (2019) · San José State University ScholarWorks (San Jose State University) · doi:10.31979/etd.fhhr-49pm · Cited by 34
Analysis of Length Normalization in End-to-End Speaker Verification System
Cai, W., Chen, J., & Li, M. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-92 · Cited by 39
Multi-Class Spectral Clustering with Overlaps for Speaker Diarization
Raj, D., Huang, Z., & Khudanpur, S. P. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383602 · Cited by 33
“It was trained on VoxCeleb data [34] with simulated room impulse responses [35] using the Kaldi toolkit [36], and released as part of the CHiME-6 baseline [27].”
MethodImproving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning
Wu, H., Xu, L., Liu, A. T., Wu, Z., Meng, H. M. L., & Lee, H.-Y. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3133189 · Cited by 49
X-vector anonymization using autoencoders and adversarial training for preserving speech privacy
Perero-Codosero, J. M., Espinoza-Cuadros, F., & Gómez, L. A. H. (2022) · Computer Speech & Language · doi:10.1016/j.csl.2022.101351 · Cited by 48
Exploring racial and gender disparities in voice biometrics
Chen, X., Li, Z., Setlur, S., & Xu, W. (2022) · Scientific Reports · doi:10.1038/s41598-022-06673-y · Cited by 36
Lip Sync Matters: A Novel Multimodal Forgery Detector
Shahzad, S. A., Hashmi, A., Khan, S., Peng, Y.-T., Tsao, Y., & Wang, H.-M. (2022) · 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980296 · Cited by 33
“To deal with the imbalance, we added more real videos from the VoxCeleb1 dataset [32] to the real class and applied an oversampling strategy during training.”
MethodMultimodal Forgery Detection Using Ensemble Learning
Hashmi, A., Shahzad, S. A., Ahmad, W., Lin, C. W., Tsao, Y., & Wang, H.-M. (2022) · 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980255 · Cited by 32
“issue, we augmented the training samples of the real class with 16,949 video samples (shown as red in I) from the VoxCeleb1 dataset [60].”
MethodSample-Cohesive Pose-Aware Contrastive Facial Representation Learning
Liu, Y., Feng, S., Liu, S., Zhan, Y., Tao, D., Chen, Z., & Chen, Z. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02348-z · Cited by 38
“For self-supervised pre-training , we combined two large-scale and in-the-wild face-related datasets, namely the Vox-Celeb1 (Nagrani et al., 2017) and VoxCeleb2 (Ojala et al., 2002).”
Introducing phonetic information to speaker embedding for speaker verification
Liu, Y., He, L. J., Liu, J., & Johnson, M. T. (2019) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-019-0166-8 · Cited by 34
Improving Deep CNN Networks with Long Temporal Context for Text-Independent Speaker Verification
Zhao, Y. H., Zhou, T., Chen, Z., & Wu, J. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053767 · Cited by 33
“We evaluate the proposed approach on the VoxCeleb corpus [8, 9] and a Microsoft internal test set.”
MethodBai, Z., Zhang, X.-L., & Chen, J. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053674 · Cited by 32
“In the 16KHZ system, the deep embedding models were trained using the speech data extracted from the combined VoxCeleb 1 and 2 corpora [22, 25].”
MethodDeep multi-metric learning for text-independent speaker verification
Xu, J., Wang, X., Feng, B., & Liu, W. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.045 · Cited by 36
“VoxCeleb [45] VoxCeleb1 PLDA+SVM Variable Length 8.”
MethodInfluentialSelf-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization
Sang, M., Li, H., Liu, F., Arnold, A. O., & Wan, L. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747526 · Cited by 47
Kim, S.-H., Nam, H., & Park, Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747421 · Cited by 43
“The models are trained on 5994 speakers of Voxceleb2 development set [19], and we validate them using Voxceleb1 test set [18].”
BackgroundMethodInfluentialSelf-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction
Han, B., Chen, Z., & Qian, Y. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-742 · Cited by 46
Robust Speaker Recognition Using Speech Enhancement And Attention Model
Shi, Y., Huang, Q., & Hain, T. (2020) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2020-65 · Cited by 39
IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian Languages
Javed, T., Bhogale, K. S., Raman, A., Kumar, P., Kunchukuttan, A., & Khapra, M. M. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26521 · Cited by 110
Speech Emotion Recognition ‘in the Wild’ Using an Autoencoder
Dissanayake, V., Zhang, H., Billinghurst, M., & Nanayakkara, S. C. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1356 · Cited by 36
“The autoencoder model was trained with a substantial sized speech corpus from VoxCeleb, which had nearly 150,000 uttarances.”
MethodFamilies in Wild Multimedia: A Multimodal Database for Recognizing Kinship
Robinson, J. P., Khan, Z., Yin, Y., Shao, M., & Fu, Y. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3103074 · Cited by 36
End-to-End Speaker-Attributed ASR with Transformer
Kanda, N., Ye, G., Gaur, Y., Wang, X., Meng, Z., Chen, Z., & Yoshioka, T. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-101 · Cited by 68
FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing
Zhang, J., Li, X., Wan, Z., Wang, C., & Liao, J. (2022) · SIGGRAPH Asia Conference Papers · doi:10.1145/3550469.3555404 · Cited by 56
“Our training data involves 213 talking videos which are selected from the VoxCeleb dataset [Nagrani et al. 2017].”
MethodInfluentialCombining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection
Attorresi, L., Salvi, D., Borrelli, C., Bestagini, P., & Tubaro, S. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-37742-6_21 · Cited by 30
Wang, X., Delgado, H., Tak, H., Jung, J.-W., Shim, H.-J., Todisco, M., Kukanov, I., Liu, X., Sahidullah, M., Kinnunen, T., et al. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2025.101825 · Cited by 30
“Illustrated to the right in Figure 6 is a pair of additional t-SNE plots, the difference between which shows the impact of encoding/compression.”
Wang, S., Chen, Z., Lee, K. A., Qian, Y., & Li, H. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3492793 · Cited by 53
“The common approach directly integrates pretrained representations alongside text into a multispeaker speech synthesis system [13], [298], [324], ensuring that the synthesized speech retains the vocal features of a particular speaker.”
Attention Mechanism in Speaker Recognition: What Does it Learn in Deep Speaker Embedding?
Wang, Q., Okabe, K., Lee, K. A., Yamamoto, H., & Koshinaka, T. (2018) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639586 · Cited by 30
Natural Language Processing: Speaker, Language, and Gender Identification with LSTM
Nammous, M. K., & Saeed, K. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-3702-4_9 · Cited by 30
Learning Facial Representations from the Cycle-consistency of Face
Chang, J.-R., Chen, Y., & Chiu, W.-C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00954 · Cited by 45
“The proposed model is trained on the combination of VoxCeleb1 [29] and VoxCeleb2 [5] datasets, in which both datasets are built upon videos of interviews.”
MethodInfluentialSelf-Supervised 3D Face Reconstruction via Conditional Estimation
Wen, Y., Liu, W., Raj, B., & Singh, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01304 · Cited by 29
“Images are from the video frames in VoxCeleb1 dataset [26]”
MethodUnsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast
Zhu, B., Xu, K., Wang, C., Qin, Z., Sun, T., Wang, H., & Peng, Y. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/526 · Cited by 36
ATST: Audio Representation Learning with Teacher-Student Transformer
Xian, L. I., & Li, X. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10126 · Cited by 47
“We use the Voxceleb1 dataset [22], with 1,251 speakers.”
MethodAdapting Self-Supervised Models to Multi-Talker Speech Recognition Using Speaker Embeddings
Huang, Z., Raj, D., Garcia, L. P., & Khudanpur, S. P. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097139 · Cited by 49
“For our experiments, all these three embedding extractors were pre-trained on the VoxCeleb [34, 35] dataset, with a dimension of 400, 512, and 256 for i-vectors, x-vectors, and ECAPA-TDNN embeddings, respectively.”
MethodKim, G., Shim, H., Kim, H., Choi, Y., Kim, J., & Yang, E. (2023) · 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/cvpr52729.2023.00590 · Cited by 59
NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification
Heo, H.-J., Shin, U.-H., Lee, R., Cheon, Y., & Park, H. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447037 · Cited by 43
“In our experiments, training and evaluation were based on VoxCeleb1 [22] and VoxCeleb2 [13] datasets.”
MethodCycle-GANs for Domain Adaptation of Acoustic Features for Speaker Recognition
Nidadavolu, P. S., Villalba, J., & Dehak, N. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683055 · Cited by 33
“The authors in [2] approached this problem by augmenting the telephone data with microphone speech from the VoxCeleb dataset [3] and obtained a significant improvement on SITW.”
MethodUnderstanding and Visualizing Raw Waveform-Based CNNs
Muckenhirn, H., Abrol, V., Magimai.-Doss, M., & Marcel, S. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2341 · Cited by 45
“In speech or audio related classification tasks, most deep learning systems are fed with intermediate features such as Mel-frequency cepstral coefficients (MFCCs) [1], filterbank outputs with a linear [2] or Mel scale [3] and spectrograms [4, 5].”
BackgroundThe VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation
Panariello, M., Tomashenko, N., Wang, X., Miao, X., Champion, P., Nourtel, H., Todisco, M., Evans, N., Vincent, E., & Yamagishi, J. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3430530 · Cited by 71
“The majority of the training set is also in English, however VoxCeleb1-2 also contain speech from non-English speakers [4], [5].”
BackgroundPortrait4D-V2: Pseudo Multi-view Data Creates Better 4D Head Synthesizer
Deng, Y., Wang, D., & Wang, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72643-9_19 · Cited by 89
Self-Supervised Learning for Audio-Visual Speaker Diarization
Ding, Y., Xu, Y., Zhang, S.-X., Cong, Y., & Wang, L. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054376 · Cited by 41
“Recently, Nagrani presents a method for speaker identification/verification [16].”
MethodSpeakerGAN: Speaker identification with conditional generative adversarial network
Chen, L., Liu, Y., Xiao, W., Wang, Y., & Xie, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.08.040 · Cited by 34
Graph Attention Networks for Speaker Verification
Jung, J.-W., Heo, H.-S., Yu, H.-J., & Chung, J. S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414057 · Cited by 43
Self-citationWav2Spk: A Simple DNN Architecture for Learning Speaker Embeddings from Waveforms
Lin, W., & Mak, M. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1287 · Cited by 32
“The training data include the VoxCeleb1 development set and the VoxCeleb2 development set [5, 18].”
MethodA Smart Mirror for Emotion Monitoring in Home Environments
Bianco, S., Celona, L., Ciocca, G., Marelli, D., Napoletano, P., Yu, S., & Schettini, R. (2021) · Sensors · doi:10.3390/s21227453 · Cited by 36
Deep Illumination-Enhanced Face Super-Resolution Network for Low-Light Images
Guo, K., Hu, M., Ren, S., Li, F., Zhang, J., Guo, H., & Kui, X. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3495258 · Cited by 32
“We choose a video from the VoxCeleb [48] dataset and select faces from frame t to frame t+ n+ 2 in the video for visual comparisons.”
MethodSelf-Knowledge Distillation via Feature Enhancement for Speaker Verification
Liu, B., Wang, H., Chen, Z., Wang, S., & Qian, Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746529 · Cited by 36
“Our experiments are conducted on the Voxceleb1&2 [21, 22] datasets.”
MethodLanguage-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features
Lux, F., & Vu, T. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.472 · Cited by 45
DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads
Zhang, X., Wu, X., Zhai, X., Ben, X., & Tu, C. (2020) · 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/cvpr42600.2020.01235 · Cited by 44
“To systematically evaluate and analyze the performance of the DAVD-Net methodology conditioned on priors of different strengths, we conduct extensive experiments on two datasets: Obama dataset (single person) and VoxCeleb2 dataset (multiple persons) [21, 6].”
MethodMultimodal Self-Supervised Learning of General Audio RepresentationsPreprint
Wang, L., Luc, P., Recasens, A., Alayrac, J.-B., & van den Oord, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.12807 · Cited by 59
“For speaker identification, we consider 100 hours of the train-clean subset of Librispeech [29] with 251 speakers, and a larger one called VoxCeleb [30] containing 1251 speakers.”
Agarwal, M., Mukhopadhyay, R., Namboodiri, V., & Jawahar, C. V. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00515 · Cited by 28
Pose-disentangled Contrastive Learning for Self-supervised Facial Representation
Liu, Y., Wang, W., Zhan, Y., Feng, S., Liu, K., & Chen, Z. (2023) · 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/cvpr52729.2023.00937 · Cited by 51
Self-attention based speaker recognition using Cluster-Range Loss
Bian, T., Chen, F., & Li, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.08.046 · Cited by 30
Speaker Detection in the Wild: Lessons Learned from JSALT 2019
Garcia, L. P., Villalba, J., Bredin, H., Du, J., Castán, D., Cristià, A., Bullock, L., Guo, L., Okabe, K., Nidadavolu, P. S., et al. (2020) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2020-59 · Cited by 30
Zeinali, H., Burget, L., & Černocký, J. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003882 · Cited by 31
“In text-independent speaker verification, large-scale datasets are available, thanks to the NIST SRE evaluations and other data collection projects such as VoxCeleb [1].”
FoolHD: Fooling Speaker Identification by Highly Imperceptible Adversarial Disturbances
Shamsabadi, A. S., Teixeira, F. S., Abad, A., Raj, B., Cavallaro, A., & Trancoso, I. M. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413760 · Cited by 34
Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification
Mun, S. H., Jung, J.-W., Han, M. H., & Kim, N. S. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10023305 · Cited by 40
“The evaluation is performed using VoxCeleb1 dataset [3] where we report the equal error rate (EER) and the minimum detection cost function (MinDCF) for three different evaluation protocols, namely, VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H.”
MethodWang, D., Xiao, X., Kanda, N., Yoshioka, T., & Wu, J. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095185 · Cited by 34
“The TS-VAD models were first pre-trained with simulated conversations based on the VoxCeleb1 dev set [31] and the VoxCeleb2 dev and test sets [32].”
MethodGolden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification
Liu, T., Lee, K. A., Wang, Q., & Li, H. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3385277 · Cited by 43
Robust Speech Activity Detection in Movie Audio: Data Resources and Experimental Evaluation
Hebbar, R., Somandepalli, K., & Narayanan, S. S. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682532 · Cited by 29
“Popular CNN architectures such as VGG [23] and Res-net [24] have been replicated with some modifications for various speech-based tasks with impressive results [16, 25, 26].”
MethodHierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise LossPreprint
Chen, L., Maddox, R. K., Duan, Z., & Xu, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03820 · Cited by 32
“For example, in web videos [5, 24] (e.g., LRW and VoxCeleb datasets), speakers move significantly when they are talking.”
BackgroundMethodThe VoicePrivacy 2020 Challenge Evaluation PlanPreprint
Tomashenko, N., Srivastava, B. M. L., Wang, X., Vincent, E., Nautsch, A., Yamagishi, J., Evans, N., Patino, J., Bonastre, J.-F., Noé, .-G., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.07123 · Cited by 39
“• VoxCeleb-1,2 5 [8, 9] is an audiovisual corpus extracted from videos uploaded to YouTube and designed for speaker verification research.”
BackgroundCai, D., & Li, M. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3419426 · Cited by 42
Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification
Jung, Y., Kim, Y., Lim, H., Choi, Y., & Kim, H. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2177 · Cited by 28
“VGG-M [14] is trained using contrastive loss with the TAP layer.”
MethodInfluentialVoice Anonymization in Urban Sound Recordings
Cohen-Hadria, A., Cartwright, M., McFee, B., & Bello, J. P. (2019) · Machine learning for signal processing ... · doi:10.1109/mlsp.2019.8918913 · Cited by 27
“We constructed our own separated datasets using SONYC [2] recordings of New York City as the background, and two sources of foreground voice recordings: VoxCeleb [11] celebrity voices recordings and LibriSpeech audio book speech recordings [12].”
MethodAM-MobileNet1D: A Portable Model for Speaker Recognition
Nunes, J. A. C., Macêdo, D., & Zanchettin, C. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207519 · Cited by 28
“VoxCeleb1 contains over 100k samples distributed in about 1.2k celebrities, and the samples were extracted from videos uploaded on YouTube.”
MethodMotion-supervised Co-Part Segmentation
Siarohin, A., Roy, S., Lathuilière, S., Tulyakov, S., Ricci, E., & Sebe, N. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412520 · Cited by 40
“We evaluate our method on two datasets: VoxCeleb and Tai-Chi-HD.”
MethodInfluentialKothapally, V., Xia, W., Ghorbani, S., Hansen, J. H. L., Xue, W., & Huang, J. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2048 · Cited by 27
EgoCom: A Multi-Person Multi-Modal Egocentric Communications Dataset
Northcutt, C. G., Zha, S., Lovegrove, S. J., & Newcombe, R. A. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3025105 · Cited by 43
“The audio features used for this task are generated from a speaker identification model trained on the Voxceleb [47] dataset.”
MethodMulti-Modal Residual Perceptron Network for Audio–Video Emotion Recognition
Chang, X., & Skarbek, W. (2021) · Sensors · doi:10.3390/s21165452 · Cited by 31
“The initialization of vocal CNN extractor were sampled from VoxCeleb dataset[37].”
MethodSparse to Dense Motion Transfer for Face Image Animation
Zhao, R., Wu, T., & Guo, G. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00226 · Cited by 39
“Meanwhile, several face video datasets such as VoxCeleb [31, 8, 32] and FaceForensics [38] are collected that facilitate the development of this challenging task.”
BackgroundMethodThe Influence of Dataset Partitioning on Dysfluency Detection Systems
Bayerl, S. P., Wagner, D., Nöth, E., Bocklet, T., & Riedhammer, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16270-1_35 · Cited by 52
“The model was trained on the VoxCeleb dataset [12].”
MethodWhat Do Audio Transformers Hear? Probing Their Representations For Language Delivery & Structure
Kumar, Y., Shah, J., Chen, C., & Shah, R. R. (2022) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw58026.2022.00120 · Cited by 50
“To this end, we perform two representative tasks: speaker recognition on Voxceleb [54] (which uses audio features primarily), and phone classification on LibriSpeech (which uses pronunciation features).”
MethodSingle-branch Network for Multimodal Training
Saeed, M. S., Nawaz, S., Khan, M. H., Zaheer, M. Z., Nandakumar, K., Yousaf, M. H., & Mahmood, A. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097207 · Cited by 50
Learning Audio-Visual Dereverberation
Chen, C., Sun, W., Harwath, D. F., & Grauman, K. L. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095818 · Cited by 43
Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-Gans
Nidadavolu, P. S., Kataria, S., Villalba, J., & Dehak, N. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003748 · Cited by 28
“For that, we used development portion of SITW and the much larger VoxCeleb1 dataset [3] as the target domain data to learn the feature mapping function.”
InfluentialWhen Automatic Voice Disguise Meets Automatic Speaker Verification
Zheng, L., Li, J., Sun, M., Zhang, X., & Zheng, T. F. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3023818 · Cited by 30
“any restoration are also given to illustrate the threat of AVD on ASV. For the ASV baseline without disguise, the standard list of trials given in Voxceleb1 is used, which has 37,720 trials in total [38]. D.!Time-Frequency features utilized in ASV After removing the silent parts of an utterance by voice activity detec…”
MethodAccentron: Foreign accent conversion to arbitrary non-native speakers using zero-shot learning
Ding, S., Zhao, G., & Gutiérrez‐Osuna, R. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101302 · Cited by 39
“Speaker encoder We trained the speaker encoder using the VoxCeleb1 corpus [79], which contains 153,516 utterances of 16 kHz speech produced by 1,251 speakers.”
MethodScalable and Efficient Neural Speech Coding: A Hybrid Design
Zhen, K., Sung, J., Lee, M. S., Beack, S., & Kim, M. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3129353 · Cited by 31
“The major motivation of employing neural networks to speech coding is twofold: to fill the performance gap between vocoders and waveform codecs towards a neartransparent speech synthesis quality; to use its trainable encoder and learn latent representations which may benefit other DNN-implemented downstream applicatio…”
BackgroundJain, R., Yiwere, M. Y., Bigioi, D., Corcoran, P., & Cucu, H. (2022) · IEEE Access · doi:10.1109/access.2022.3170836 · Cited by 31
Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers
Sun, Y., Zhou, H., Wang, K., Wu, Q., Hong, Z., Liu, J., Ding, E., Wang, J., Liu, Z., & Koike, H. (2022) · SIGGRAPH Asia Conference Papers · doi:10.1145/3550469.3555393 · Cited by 49
“The figures are selected from VoxCeleb [Nagrani et al. 2017] and VoxCeleb2 [Chung et al. 2018] ©Visual Geometry Group (CC BY).”
BackgroundMethodInfluentialSpeaker Recognition with Two-Step Multi-Modal Deep Cleansing
Tao, R., Lee, K. A., Shi, Z., & Li, H. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096814 · Cited by 30
“Note that we use the term noisy samples referring to samples with wrong labels following the terminology in [10].”
MethodInfluentialCollaborations on YouTube: From Unsupervised Detection to the Impact on Video and Channel Popularity
Koch, C., Lode, M., Stohr, D., Rizk, A., & Steinmetz, R. (2018) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3241054 · Cited by 35
“To this end, we evaluate CATANA on the VoxCeleb [19] speaker dataset.”
MethodOn the Resilience of Biometric Authentication Systems against Random Inputs
Zhao, B. Z. H., Asghar, H. J., & Kâafar, M. A. (2020) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2020.24210 · Cited by 34
Wavelet Scattering Transform and CNN for Closed Set Speaker Identification
Ghezaiel, W., Brun, L., & Lézoray, O. (2020) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp48831.2020.9287061 · Cited by 29
“Some works have proposed to directly feed networks with spectrogram bins [15] or even with raw waveforms [16], [17].”
BackgroundVoice gender recognition under unconstrained environments using self-attention
Nasef, M. M., Sauber, A. M., & Nabil, M. M. (2020) · Applied Acoustics · doi:10.1016/j.apacoust.2020.107823 · Cited by 27
Anonymization Techniques for Behavioral Biometric Data: A Survey
Hanisch, S., Arias-Cabarcos, P., Parra‐Arnau, J., & Strufe, T. (2025) · ACM Computing Surveys · doi:10.1145/3729418 · Cited by 40
“701 2014 [109] Voice Librispeech 1166 2015 [117] Voice RSR2015 300 2015 [74] Voice VoxCeleb 1251 2018 [158] Voice CSTR VCTK Corpus 110 2019 [209] Voice VCC 2016 10 2016 [137] Voice CASIA-B 124 2005 [66] Gait BEHAVE 125 2010 [51] Gait OU-ISIR 200 2012 [75] Gait EPIC-Kitchens 32 2020 [214] Gait IITMD-WFP 31 2021 [254] G…”
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.