{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:58:44Z","timestamp":1781045924184,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819571949","type":"print"},{"value":"9789819571956","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-7195-6_35","type":"book-chapter","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:25:48Z","timestamp":1781043948000},"page":"477-489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Emotional Conversation: Empowering Talking Faces with\u00a0Cohesive Expression, Gaze and\u00a0Pose Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3177-3810","authenticated-orcid":false,"given":"Jiadong","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9064-7964","authenticated-orcid":false,"given":"Feng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Burkov, E., Pasechnik, I., Grigorev, A., Lempitsky, V.: Neural head reenactment with latent pose descriptors. In: CVPR, pp. 13786\u201313795 (2020)","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"35_CR2","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: CVPR, pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"35_CR3","doi-asserted-by":"publisher","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Workshop on Multi-view Lip-reading, ACCV, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Drobyshev, N., Chelishev, J., Khakhulin, T., Ivakhnenko, A., Lempitsky, V., Zakharov, E.: Megaportraits: one-shot megapixel neural head avatars. In: ACM MM, pp. 2663\u20132671 (2022)","DOI":"10.1145\/3503161.3547838"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Du, C., et al.: Dae-talker: High fidelity speech-driven talking face generation with diffusion autoencoder. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4281\u20134289 (2023)","DOI":"10.1145\/3581783.3613753"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: Faceformer: speech-driven 3d facial animation with transformers. In: CVPR, pp. 18770\u201318780 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Gu, K., Zhou, Y., Huang, T.: Flnet: Landmark driven fetching and learning network for faithful talking facial animation synthesis. In: AAAI. vol.\u00a034, pp. 10861\u201310868 (2020)","DOI":"10.1609\/aaai.v34i07.6717"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Gururani, S., Mallya, A., Wang, T.C., Valle, R., Liu, M.Y.: Space: speech-driven portrait animation with controllable expression. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20914\u201320923 (2023)","DOI":"10.1109\/ICCV51070.2023.01912"},{"key":"35_CR9","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. NIPS 30 (2017)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Hong, F.T., Zhang, L., Shen, L., Xu, D.: Depth-aware generative adversarial network for talking head video generation. In: CVPR, pp. 3397\u20133406 (2022)","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: Eamm: One-shot emotional talking face via audio-based emotion-aware motion model. In: ACM SIGGRAPH, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530745"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: Audio-driven emotional video portraits. In: CVPR, pp. 14080\u201314089 (2021)","DOI":"10.1109\/CVPR46437.2021.01386"},{"issue":"4","key":"35_CR13","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. TOG 36(4), 1\u201312 (2017)","journal-title":"TOG"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Li-net: Large-pose identity-preserving face reenactment network. In: ICME, pp.\u00a01\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428233"},{"key":"35_CR15","doi-asserted-by":"publisher","unstructured":"Liu, X., Xu, Y., Wu, Q., Zhou, H., Wu, W., Zhou, B.: Semantic-aware implicit neural audio-driven video portrait generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 106\u2013125. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_7","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"35_CR16","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: ACM MM, pp. 484\u2013492 (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Shen, S., et al.: Difftalk: Crafting diffusion models for generalized audio-driven portraits animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1982\u20131991 (2023)","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: CVPR, pp. 13653\u201313662 (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"35_CR19","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1109\/TIFS.2022.3146783","volume":"17","author":"L Song","year":"2022","unstructured":"Song, L., Wu, W., Qian, C., He, R., Loy, C.C.: Everybody\u2019s talkin\u2019: let me talk as you want. IEEE Trans. Inf. Forensics Secur. 17, 585\u2013598 (2022)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Tan, S., Ji, B., Pan, Y.: Emmn: emotional motion memory network for audio-driven emotional talking face generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22146\u201322156 (2023)","DOI":"10.1109\/ICCV51070.2023.02024"},{"issue":"4","key":"35_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073699","volume":"36","author":"S Taylor","year":"2017","unstructured":"Taylor, S., Kim, T., Yue, Y., Mahler, M., Krahe, J., Rodriguez, A.G., Hodgins, J., Matthews, I.: A deep learning approach for generalized speech animation. TOG 36(4), 1\u201311 (2017)","journal-title":"TOG"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: End-to-end speech-driven facial animation with temporal gans. In: CVPR Workshop (2019)","DOI":"10.1007\/s11263-019-01251-8"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Wang, D., Deng, Y., Yin, Z., Shum, H.Y., Wang, B.: Progressive disentangled representation learning for fine-grained controllable talking head synthesis. In: CVPR, pp. 17979\u201317989 (2023)","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Lipformer: High-fidelity and generalizable talking face generation with a pre-learned facial codebook. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13844\u201313853 (2023)","DOI":"10.1109\/CVPR52729.2023.01330"},{"key":"35_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1007\/978-3-030-58589-1_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Wang","year":"2020","unstructured":"Wang, K., Wu, Q., Song, L., Yang, Z., Wu, W., Qian, C., He, R., Qiao, Yu., Loy, C.C.: MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face Generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 700\u2013717. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_42"},{"key":"35_CR26","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. IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/152"},{"key":"35_CR27","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: CVPR, pp. 10039\u201310049 (2021)","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"35_CR28","unstructured":"Wang, Y., Yang, D., Bremond, F., Dantcheva, A.: Latent image animator: learning to animate images via latent space navigation (2022)"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhou, S., Jia, J., Xing, J., Wen, Q., Wen, X.: Speech-driven 3d face animation with composite and regional facial movements. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6822\u20136830 (2023)","DOI":"10.1145\/3581783.3611775"},{"key":"35_CR30","unstructured":"Xiang, S., et al.: One-shot identity-preserving portrait reenactment. arXiv preprint arXiv:2004.12452 (2020)"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Xu, C., et al.: High-fidelity generalized emotional talking face generation with multi-modal emotion space learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6609\u20136619 (2023)","DOI":"10.1109\/CVPR52729.2023.00639"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., Wang, X.: Talking face generation by adversarially disentangled audio-visual representation. In: AAAI, vol.\u00a033, pp. 9299\u20139306 (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, Y., Wu, W., Loy, C.C., Wang, X., Liu, Z.: Pose-controllable talking face generation by implicitly modularized audio-visual representation. In: CVPR, pp. 4176\u20134186 (2021)","DOI":"10.1109\/CVPR46437.2021.00416"},{"issue":"6","key":"35_CR34","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., Li, D.: Makelttalk: speaker-aware talking-head animation. TOG 39(6), 1\u201315 (2020)","journal-title":"TOG"}],"container-title":["Lecture Notes in Computer Science","Extended Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7195-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:25:53Z","timestamp":1781043953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7195-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819571949","9789819571956"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7195-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICXR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Extended Reality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","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":"1 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icxr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icxr.net\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}