{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T16:35:48Z","timestamp":1758040548665,"version":"3.44.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032045546"},{"type":"electronic","value":"9783032045553"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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\/978-3-032-04555-3_15","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T08:55:58Z","timestamp":1757580958000},"page":"179-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Driven Talking Head Generation with\u00a0Emotion Based on\u00a0FLAME Geometry Model"],"prefix":"10.1007","author":[{"given":"Yahui","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liejun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinfeng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjie","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"issue":"1","key":"15_CR1","doi-asserted-by":"publisher","first-page":"25","DOI":"10.18034\/ajase.v8i1.9","volume":"8","author":"NB Bynagari","year":"2019","unstructured":"Bynagari, N.B.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. Asian J. Appl. Sci. Eng. 8(1), 25\u201334 (2019)","journal-title":"Asian J. Appl. Sci. Eng."},{"key":"15_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"15_CR3","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":"15_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"15_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"issue":"9","key":"15_CR6","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"FA Croitoru","year":"2023","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10850\u201310869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"15_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459936","volume":"40","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM Trans. Graph. (ToG) 40(4), 1\u201313 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Gan, Y., Yang, Z., Yue, X., Sun, L., Yang, Y.: Efficient emotional adaptation for audio-driven talking-head generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22634\u201322645 (2023)","DOI":"10.1109\/ICCV51070.2023.02069"},{"issue":"11","key":"15_CR9","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":"15_CR10","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Hamilton, J.D.: State-space models. In: Handbook of Econometrics, vol. 4, pp. 3039\u20133080 (1994)","DOI":"10.1016\/S1573-4412(05)80019-4"},{"key":"15_CR12","unstructured":"Hu, Z., Xu, D.: Videocontrolnet: a motion-guided video-to-video translation framework by using diffusion model with controlnet. arXiv preprint arXiv:2307.14073 (2023)"},{"key":"15_CR13","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 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530745"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: Audio-driven emotional video portraits. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14080\u201314089 (2021)","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. 36(6), 194-1 (2017)","DOI":"10.1145\/3130800.3130813"},{"key":"15_CR16","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Meng, D., Peng, X., Wang, K., Qiao, Y.: Frame attention networks for facial expression recognition in videos. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 3866\u20133870. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Mukhopadhyay, S., Suri, S., Gadde, R.T., Shrivastava, A.: Diff2lip: audio conditioned diffusion models for lip-synchronization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5292\u20135302 (2024)","DOI":"10.1109\/WACV57701.2024.00521"},{"key":"15_CR19","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":"15_CR20","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Sinha, S., Biswas, S., Yadav, R., Bhowmick, B.: Emotion-controllable generalized talking face generation. arXiv preprint arXiv:2205.01155 (2022)","DOI":"10.24963\/ijcai.2022\/184"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Sun, Z., Xuan, Y., Liu, F., Xiang, Y.: FG-EmoTalk: talking head video generation with fine-grained controllable facial expressions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 5043\u20135051 (2024)","DOI":"10.1609\/aaai.v38i5.28309"},{"key":"15_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-031-72658-3_23","volume-title":"European Conference on Computer Vision","author":"S Tan","year":"2024","unstructured":"Tan, S., Ji, B., Bi, M., Pan, Y.: EDTalk: efficient disentanglement for emotional talking head synthesis. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15064, pp. 398\u2013416. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_23"},{"key":"15_CR24","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., et al.: 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":"15_CR25","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, L., Ding, Y., Yu, X.: One-shot talking face generation from single-speaker audio-visual correlation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2531\u20132539 (2022)","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"15_CR26","first-page":"15028","volume":"37","author":"Y Wang","year":"2025","unstructured":"Wang, Y., et al.: Cliploss and norm-based data selection methods for multimodal contrastive learning. Adv. Neural. Inf. Process. Syst. 37, 15028\u201315069 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR27","unstructured":"Xu, M., et al.: Hallo: hierarchical audio-driven visual synthesis for portrait image animation. arXiv preprint arXiv:2406.08801 (2024)"},{"key":"15_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/978-3-031-72983-6_18","volume-title":"European Conference on Computer Vision","author":"B Zhang","year":"2024","unstructured":"Zhang, B., Zhang, P., Dong, X., Zang, Y., Wang, J.: Long-clip: Unlocking the long-text capability of clip. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15109, pp. 310\u2013325. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72983-6_18"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zhang, X., Cheng, N., Yu, J., Xiao, J., Wang, J.: Emotalker: emotionally editable talking face generation via diffusion model. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8276\u20138280. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447505"},{"key":"15_CR30","unstructured":"Zhang, J., Mai, W., Zhang, Z.: Emodiffhead: continuously emotional control in talking head generation via diffusion. arXiv preprint arXiv:2409.07255 (2024)"},{"key":"15_CR31","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4176\u20134186 (2021)","DOI":"10.1109\/CVPR46437.2021.00416"},{"issue":"6","key":"15_CR32","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. ACM Trans. Graph. (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04555-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T08:56:06Z","timestamp":1757580966000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04555-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045546","9783032045553"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04555-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}