{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:41:02Z","timestamp":1757619662361,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819699070"},{"type":"electronic","value":"9789819699087"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9908-7_29","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T16:26:27Z","timestamp":1753374387000},"page":"349-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EC Speaker: Speech-Driven 3D Facial Animation with Latent Emotion Constraints"],"prefix":"10.1007","author":[{"given":"Chen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Wenyuan","family":"Ying","sequence":"additional","affiliation":[]},{"given":"Tianyang","family":"Dong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"issue":"1","key":"29_CR1","doi-asserted-by":"publisher","first-page":"3346136","DOI":"10.1155\/2021\/3346136","volume":"2021","author":"L Xu","year":"2021","unstructured":"Xu, L.: [Retracted] fast modelling algorithm for realistic three-dimensional human face for film and television animation. Complexity 2021(1), 3346136 (2021)","journal-title":"Complexity"},{"issue":"4","key":"29_CR2","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. Graphics (ToG) 36(4), 1\u201312 (2017)","journal-title":"ACM Trans. Graphics (ToG)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.J.: Capture, learning, and synthesis of 3D speaking styles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10101\u201310111. (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., De la Torre, F., Sheikh, Y.: MeshTalk: 3D face animation from speech using cross-modality disentanglement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1173\u20131182 (2021)","DOI":"10.1109\/ICCV48922.2021.00121"},{"issue":"11","key":"29_CR5","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"29_CR6","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Pirhayatifard, D., Toghani, M.T., Balakrishnan, G., Uribe, C.A.: Improving denoising diffusion probabilistic models via exploiting shared representations. In: 2023 57th Asilomar Conference on Signals, Systems, and Computers, pp. 789\u2013793. IEEE (2023)","DOI":"10.1109\/IEEECONF59524.2023.10476867"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Hsu, W.-N., et al.: Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Stan, S., Haque, K. I., Yumak, Z.: Facediffuser: speech-driven 3D facial animation synthesis using diffusion. In: Proceedings of the 16th ACM SIGGRAPH Conference on Motion, Interaction and Games, pp. 1\u201311 (2023)","DOI":"10.1145\/3623264.3624447"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Panayotov, V., et al.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"29_CR11","unstructured":"Baevski, A., et al.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, C., Ling, X., Deng, W.: Learn from all: Erasing attention consistency for noisy label facial expression recognition. In: European Conference on Computer Vision, pp. 418\u2013434 (2022)","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: Faceformer: speech-driven 3D facial animation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18770\u201318780 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Xing, J., Xia, M., Zhang, Y., Cun, X., Wang, J., Wong, T.T.: Codetalker: speech-driven 3D facial animation with discrete motion prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12780\u201312790 (2023)","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Haque, K. I., Yumak, Z.: Facexhubert: text-less speech-driven e (x) pressive 3D facial animation synthesis using self-supervised speech representation learning. In: Proceedings of the 25th International Conference on Multimodal Interaction, pp. 282\u2013291 (2023)","DOI":"10.1145\/3577190.3614157"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9908-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T22:04:45Z","timestamp":1757282685000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9908-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819699070","9789819699087"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9908-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}