{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T20:01:22Z","timestamp":1794081682949,"version":"4.8.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-33928-1","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T13:17:00Z","timestamp":1768828620000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Audio-driven single image talking face animation with transformers"],"prefix":"10.1038","volume":"16","author":[{"given":"Yixin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xizhong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"issue":"5","key":"33928_CR1","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1109\/TCSVT.2004.826760","volume":"14","author":"PS Aleksic","year":"2004","unstructured":"Aleksic, P. S. & Katsaggelos, A. K. Speech-to-video synthesis using mpeg-4 compliant visual features. IEEE Trans. Circuits Syst. Video Technol. 14(5), 682\u2013692 (2004).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"33928_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, L., Li, G., Seide, F. & Soong, F.K. A new language independent, photo-realistic talking head driven by voice only. In: Interspeech 2743, 2747 (2013).","DOI":"10.21437\/Interspeech.2013-629"},{"issue":"4","key":"33928_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073699","volume":"36","author":"S Taylor","year":"2017","unstructured":"Taylor, S. et al. A deep learning approach for generalized speech animation. ACM Trans. Graph. 36(4), 1\u201311 (2017).","journal-title":"ACM Trans. Graph."},{"key":"33928_CR4","unstructured":"Chung, J.S., Jamaludin, A. & Zisserman, A. You said that? arXiv preprint arXiv:1705.02966 (2017)."},{"key":"33928_CR5","doi-asserted-by":"crossref","unstructured":"KR, P. et al. Towards automatic face-to-face translation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1428\u20131436 (2019).","DOI":"10.1145\/3343031.3351066"},{"key":"33928_CR6","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P. & Jawahar, C. A lip sync expert is all you need for speech to lip generation in the wild. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 484\u2013492 (2020).","DOI":"10.1145\/3394171.3413532"},{"key":"33928_CR7","doi-asserted-by":"crossref","unstructured":"Mittal, G. & Wang, B. Animating face using disentangled audio representations. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3290\u20133298 (2020).","DOI":"10.1109\/WACV45572.2020.9093527"},{"key":"33928_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, W. et al. Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8652\u20138661 (2023).","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"33928_CR9","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 2998-6008  (2017)."},{"key":"33928_CR10","doi-asserted-by":"crossref","unstructured":"Chung, J.S. & Zisserman, A. Out of time: automated lip sync in the wild. In: Asian Conference on Computer Vision, pp. 251\u2013263 (Springer, 2016).","DOI":"10.1007\/978-3-319-54427-4_19"},{"issue":"4","key":"33928_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073658","volume":"36","author":"T Karras","year":"2017","unstructured":"Karras, T., Aila, T., Laine, S., Herva, A. & Lehtinen, J. Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Trans. Graph. 36(4), 1\u201312 (2017).","journal-title":"ACM Trans. Graph."},{"issue":"6","key":"33928_CR12","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y. et al. Makelttalk: speaker-aware talking-head animation. ACM Trans. Graph. 39(6), 1\u201315 (2020).","journal-title":"ACM Trans. Graph."},{"key":"33928_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, H. et al. Pose-controllable talking face generation by implicitly modularized audio-visual representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4176\u20134186 (2021).","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"33928_CR14","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, L., Ding, Y., Fan, C. & Yu, X. Audio2head: Audio-driven one-shot talking-head generation with natural head motion. arXiv preprint arXiv:2107.09293 (2021).","DOI":"10.24963\/ijcai.2021\/152"},{"issue":"13","key":"33928_CR15","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.3390\/electronics14132684","volume":"14","author":"X Wang","year":"2025","unstructured":"Wang, X. et al. Multimodal feature-guided audio-driven emotional talking face generation. Electronics 14(13), 2684 (2025).","journal-title":"Electronics"},{"key":"33928_CR16","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"33928_CR17","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.R., Fan, Q. & Panda, R. Crossvit: Cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021).","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"33928_CR18","unstructured":"Chu, X., Tian, Z., Zhang, B., Wang, X. & Shen, C. Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)."},{"key":"33928_CR19","unstructured":"Touvron, H. et al. Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357 (PMLR, 2021)."},{"key":"33928_CR20","doi-asserted-by":"crossref","unstructured":"Carion, N. et al. End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229 (Springer, 2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"33928_CR21","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E. et al. Segformer: Simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. Process. Syst. 34, 12077\u201312090 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"33928_CR22","unstructured":"Jiang, Y., Chang, S. & Wang, Z. Transgan: Two transformers can make one strong gan. arXiv preprint arXiv:2102.070741(3) (2021)."},{"key":"33928_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H. & Koltun, V. Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021).","DOI":"10.1109\/ICCV48922.2021.01595"},{"issue":"2","key":"33928_CR24","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo, M.-H. et al. Pct: Point cloud transformer. Comput. Vis. Media 7(2), 187\u2013199 (2021).","journal-title":"Comput. Vis. Media"},{"key":"33928_CR25","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L. & Liu, Z. End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021).","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"33928_CR26","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R. & Ommer, B. Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021).","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"33928_CR27","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Cao, P. & Hilliges, O. A spatio-temporal transformer for 3d human motion prediction. In: 2021 International Conference on 3D Vision (3DV), pp. 565\u2013574 (IEEE, 2021).","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"33928_CR28","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U. et al. Text2gestures: A transformer-based network for generating emotive body gestures for virtual agents. In: 2021 IEEE Virtual Reality and 3D User Interfaces (VR), pp. 1\u201310 (IEEE, 2021).","DOI":"10.1109\/VR50410.2021.00037"},{"key":"33928_CR29","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J. & Varol, G. Action-conditioned 3d human motion synthesis with transformer vae. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"33928_CR30","unstructured":"Li, J. et la. Learning to generate diverse dance motions with transformer. arXiv preprint arXiv:2008.08171 (2020)."},{"key":"33928_CR31","unstructured":"Li, R., Yang, S., Ross, D.A. & Kanazawa, A. Learn to dance with aist++: Music conditioned 3d dance generation. arXiv preprint arXiv:2101.087792(3) (2021)."},{"issue":"6","key":"33928_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480570","volume":"40","author":"G Valle-P\u00e9rez","year":"2021","unstructured":"Valle-P\u00e9rez, G. et al. Transflower: probabilistic autoregressive dance generation with multimodal attention. ACM Trans. Graph. 40(6), 1\u201314 (2021).","journal-title":"ACM Trans. Graph."},{"key":"33928_CR33","doi-asserted-by":"crossref","unstructured":"Blanz, V. & Vetter, T. A morphable model for the synthesis of 3d faces. In: Seminal Graphics Papers: Pushing the Boundaries 2, 157\u2013164 (2023).","DOI":"10.1145\/3596711.3596730"},{"key":"33928_CR34","doi-asserted-by":"crossref","unstructured":"Deng, Y. et al. Accurate 3d face reconstruction with weakly-supervised learning: From single image to image set. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 0\u20130 (2019).","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"33928_CR35","doi-asserted-by":"crossref","unstructured":"Gerig, T. et al. Morphable face models-an open framework. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 75\u201382 (IEEE, 2018).","DOI":"10.1109\/FG.2018.00021"},{"key":"33928_CR36","doi-asserted-by":"crossref","unstructured":"Ma, Y. et al. Styletalk: One-shot talking head generation with controllable speaking styles. In: Proceedings of the AAAI Conference on Artificial Intelligence 37, 1896\u20131904 (2023).","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"33928_CR37","doi-asserted-by":"crossref","unstructured":"Liang, B. et al. Expressive talking head generation with granular audio-visual control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3387\u20133396 (2022).","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"33928_CR38","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., Uszkoreit, J. & Kaiser, \u0141. Universal transformers. arXiv preprint arXiv:1807.03819 (2018)."},{"key":"33928_CR39","unstructured":"Press, O., Smith, N.A. & Lewis, M. Train short, test long: Attention with linear biases enables input length extrapolation. arXiv preprint arXiv:2108.12409 (2021)."},{"key":"33928_CR40","unstructured":"Doersch, C. Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908 (2016)."},{"key":"33928_CR41","doi-asserted-by":"crossref","unstructured":"Wang, T.-C., Mallya, A. & Liu, M.-Y. One-shot free-view neural talking-head synthesis for video conferencing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10039\u201310049 (2021).","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"33928_CR42","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A. & Zisserman, A. Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018).","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"33928_CR43","doi-asserted-by":"crossref","unstructured":"Wang, K. et al. Mead: A large-scale audio-visual dataset for emotional talking-face generation. In: European Conference on Computer Vision, pp. 700\u2013717 (Springer, 2020).","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"33928_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y. & Fan, C. Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3661\u20133670 (2021).","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"33928_CR45","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B. & Hochreiter, S. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"33928_CR46","unstructured":"Seitzer, M. pytorch-fid: FID Score for PyTorch (2020)."},{"issue":"9","key":"33928_CR47","doi-asserted-by":"publisher","first-page":"2678","DOI":"10.1109\/TIP.2011.2131660","volume":"20","author":"ND Narvekar","year":"2011","unstructured":"Narvekar, N. D. & Karam, L. J. A no-reference image blur metric based on the cumulative probability of blur detection (cpbd). IEEE Trans. Image Process. 20(9), 2678\u20132683 (2011).","journal-title":"IEEE Trans. Image Process."},{"key":"33928_CR48","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N. & Zafeiriou, S. Arcface: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019).","DOI":"10.1109\/CVPR.2019.00482"},{"key":"33928_CR49","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z. & Xu, C. Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7832\u20137841 (2019).","DOI":"10.1109\/CVPR.2019.00802"},{"key":"33928_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J. et al. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024).","journal-title":"Neurocomputing"},{"key":"33928_CR51","unstructured":"Beltagy, I., Peters, M.E. & Cohan, A. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"33928_CR52","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H. & Ma, H. Linformer: Self-attention with linear complexity (2020). arXiv preprint arXiv:2006.04768 (2006)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33928-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33928-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33928-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T10:19:15Z","timestamp":1769595555000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33928-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["33928"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-33928-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"assertion":[{"value":"11 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"3796"}}