{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:04:07Z","timestamp":1766127847354,"version":"3.48.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62207029"],"award-info":[{"award-number":["62207029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["L223033"],"award-info":[{"award-number":["L223033"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00530-025-02022-x","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T05:40:49Z","timestamp":1760334049000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech-driven talking face video generation"],"prefix":"10.1007","volume":"31","author":[{"given":"Zhao","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tang","family":"Zhuoran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Qihan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"2022_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., et al.: 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":"2022_CR2","doi-asserted-by":"crossref","unstructured":"Yin, F., Zhang, Y., Cun, X., et al.: Styleheat: one-shot high-resolution editable talking face generation via pre-trained stylegan. In: European Conference on Computer Vision, pp. 85\u2013101. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"2022_CR3","doi-asserted-by":"crossref","unstructured":"Badshah, A.M., Ahmad, J., Rahim, N., et al.: Speech emotion recognition from spectrograms with deep convolutional neural network. In: International Conference on Platform Technology and Service (PlatCon), pp. 1\u20135. (2017)","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"2022_CR4","doi-asserted-by":"crossref","unstructured":"Wu, X., Liu, S., Cao, Y., et al.: Speech emotion recognition using capsule networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6695\u20136699. (2019)","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"2022_CR5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.specom.2020.03.005","volume":"120","author":"Z Yao","year":"2020","unstructured":"Yao, Z., Wang, Z., Liu, W., et al.: Speech emotion recognition using fusion of three multi-task learning-based classifiers: HSF-DNN, MS-CNN and LLD-RNN. Speech Commun. 120, 11\u201319 (2020)","journal-title":"Speech Commun."},{"key":"2022_CR6","unstructured":"Lan, Z., Chen, M., Goodman, S., et al.: Albert: A lite bert for self-supervised learning of language representations. arXiv (2019)"},{"key":"2022_CR7","doi-asserted-by":"publisher","unstructured":"India, M., Safari, P., Hernando, J.: Double multi-head attention for speaker verification. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, pp. 6144\u20136148 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414877.","DOI":"10.1109\/ICASSP39728.2021.9414877"},{"issue":"22","key":"2022_CR8","doi-asserted-by":"publisher","first-page":"6688","DOI":"10.3390\/s20226688","volume":"20","author":"S Lee","year":"2020","unstructured":"Lee, S., Han, D.K., Ko, H.: Fusion-ConvBERT: parallel convolution and BERT fusion for speech emotion recognition. Sensors. 20(22), 6688 (2020)","journal-title":"Sensors"},{"key":"2022_CR9","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, M., Qi, W., et al.: A novel end-to-end speech emotion recognition network with stacked transformer layers. In: IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP). IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414314"},{"key":"2022_CR10","doi-asserted-by":"publisher","unstructured":"Parisae, V., Bhuvanam, S.N.: Stacked U-Net with time-frequency attention and deep connection net for single channel speech enhancement. Int. J. Image Graph. https:\/\/doi.org\/10.1142\/S0219467825500676","DOI":"10.1142\/S0219467825500676"},{"key":"2022_CR11","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/s11042-024-19076-0","volume":"84","author":"V Parisa\u00e9","year":"2025","unstructured":"Parisa\u00e9, V., Bhavanam, S.N.: Adaptive attention mechanism for single channel speech enhancement. Multimed. Tools Appl. 84, 831\u2013856 (2025). https:\/\/doi.org\/10.1007\/s11042-024-19076-0","journal-title":"Multimedia Tools Appl."},{"key":"2022_CR12","doi-asserted-by":"publisher","first-page":"10907","DOI":"10.3233\/JIFS-233312","volume":"46","author":"V Parisae","year":"2024","unstructured":"Parisae, V., Bhavanam, S.N.: Multi scale encoder-decoder network with time frequency attention and S-TCN for single channel speech enhancement. J. Intell. Fuzzy Syst. 46, 10907\u201310922 (2024). https:\/\/doi.org\/10.3233\/JIFS-233312","journal-title":"J. Intell. Fuzzy Syst."},{"key":"2022_CR13","doi-asserted-by":"publisher","unstructured":"Parisae, V., Bhavanam, S.N., Devi, M.V.: Progressive learning framework for speech enhancement using multi-scale convolution and S-TCN. In: 8th International Conference on Inventive Systems and Control (ICISC), vol. 2024, pp. 21. IEEE, Coimbatore, India (2024). https:\/\/doi.org\/10.1109\/ICISC62624.2024.00021","DOI":"10.1109\/ICISC62624.2024.00021"},{"key":"2022_CR14","doi-asserted-by":"crossref","unstructured":"Sinha, S., Biswas, S., Yadav, R., et al.: Emotion-controllable generalized talking face generation. arXiv preprint arXiv:2205.01155 (2022)","DOI":"10.24963\/ijcai.2022\/184"},{"key":"2022_CR15","doi-asserted-by":"publisher","first-page":"3480","DOI":"10.1109\/TMM.2021.3099900","volume":"24","author":"SE Eskimez","year":"2021","unstructured":"Eskimez, S.E., Zhang, Y., Duan, Z.: Speech driven talking face generation from a single image and an emotion condition. IEEE Trans. Multimedia. 24, 3480\u20133490 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"2022_CR16","doi-asserted-by":"crossref","unstructured":"Goyal, S., Bhagat, S., Uppal, S., et al.: Emotionally enhanced talking face generation. In: Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice, pp. 81\u201390. (2023)","DOI":"10.1145\/3607541.3616812"},{"key":"2022_CR17","unstructured":"Liang, J., Lu, F.: Emotional conversation: empowering talking faces with cohesive expression, gaze and pose generation. arXiv preprint arXiv:2406.07895 (2024)"},{"key":"2022_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H., Jia, X., Cao, X.: EAT-Face: emotion-controllable audio-driven talking face generation via diffusion model. In: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), pp. 1\u201310. IEEE (2024)","DOI":"10.1109\/FG59268.2024.10581957"},{"key":"2022_CR19","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., Bulut, M., Lee, C.C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Evaluation"},{"issue":"4","key":"2022_CR20","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., et al.: Crema-d: crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2022_CR21","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. In: Advances in Neural Information Processing Systems, vol. 30, pp. 6627-6638 (2017)"},{"key":"2022_CR22","doi-asserted-by":"crossref","unstructured":"Narvekar, N.D., Karam, L.J.: A no-reference perceptual image sharpness metric based on a cumulative probability of blur. In: International Workshop on Quality of Multimedia Experience, pp. 87\u201391. (2009)","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"2022_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139. (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2022_CR24","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Computer Vision\u2013ACCV 2016 Workshops: ACCV 2016 International Workshops, Taipei, Taiwan, November 20\u201324, 2016, Revised Selected Papers, Part II 13, pp. 251\u2013263. Springer International Publishing (2017)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"2022_CR25","doi-asserted-by":"crossref","unstructured":"Aftab, A., Morsali, A., Ghaemmaghami, S., et al.: LIGHT-SERNET: a lightweight fully convolutional neural network for speech emotion recognition. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6912-6916. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746679"},{"key":"2022_CR26","doi-asserted-by":"crossref","unstructured":"Ye, J., Wen, X.C., Wei, Y., et al.: Temporal modeling matters: a novel temporal emotional modeling approach for speech emotion recognition. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"2022_CR27","doi-asserted-by":"crossref","unstructured":"Tang, X., Lin, Y., Dang, T., et al.: Speech emotion recognition via CNN-transformer and multidimensional attention mechanism. arXiv preprint arXiv:2403.04743 (2024)","DOI":"10.1016\/j.specom.2025.103242"},{"issue":"6","key":"2022_CR28","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., Wang, C., Chen, Z., et al.: Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE J. Selec. Topics Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Selec. Topics Signal Process."},{"key":"2022_CR29","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., et al.: Data2vec: A general framework for self-supervised learning in speech, vision and Language. In: International conference on machine learning, pp. 1298\u20131312. PMLR (2022)"},{"key":"2022_CR30","unstructured":"Baevski, A., Babu, A., Hsu, W.N., et al.: Efficient self-supervised learning with contextualized target representations for vision, speech and Language. In: International conference on machine learning, pp. 1416\u20131429. PMLR (2023)"},{"key":"2022_CR31","doi-asserted-by":"publisher","first-page":"112123","DOI":"10.1016\/j.knosys.2024.112123","volume":"299","author":"H Li","year":"2024","unstructured":"Li, H., Zhang, X., Duan, S., et al.: Speech emotion recognition based on bi-directional acoustic\u2013articulatory conversion. Knowl. Based Syst. 299, 112123 (2024)","journal-title":"Knowl. Based Syst."},{"key":"2022_CR32","doi-asserted-by":"publisher","first-page":"0073","DOI":"10.34133\/icomputing.0073","volume":"3","author":"S Shen","year":"2024","unstructured":"Shen, S., Liu, F., Wang, H., et al.: Temporal shift module with pretrained representations for speech emotion recognition. Intell. Comput. 3, 0073 (2024)","journal-title":"Intell. Comput."},{"issue":"14","key":"2022_CR33","doi-asserted-by":"publisher","first-page":"2689","DOI":"10.3390\/electronics13142689","volume":"13","author":"C Wang","year":"2024","unstructured":"Wang, C., Shen, X.: Feature-enhanced multi-task learning for speech emotion recognition using decision trees and LSTM. Electronics. 13(14), 2689 (2024)","journal-title":"Electronics"},{"key":"2022_CR34","doi-asserted-by":"crossref","unstructured":"Prajwal, K.R., Mukhopadhyay, R., Namboodiri, V.P., et al.: 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"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02022-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02022-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02022-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:59:35Z","timestamp":1766127575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02022-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2022"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02022-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"22 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2025","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":"Conflict of interest"}}],"article-number":"442"}}