{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:17:04Z","timestamp":1757625424636,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032025470"},{"type":"electronic","value":"9783032025487"}],"license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"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\/978-3-032-02548-7_9","type":"book-chapter","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:39:33Z","timestamp":1755754773000},"page":"96-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Emotion-Aware Speech-Driven Facial Avatar Animation via\u00a0Joint Blendshape Prediction and\u00a0Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Juan Camilo","family":"V\u00e1squez-Correa","sequence":"first","affiliation":[]},{"given":"Ander","family":"Gonz\u00e1lez-Docasal","sequence":"additional","affiliation":[]},{"given":"Aritz","family":"Lasarguren","sequence":"additional","affiliation":[]},{"given":"Jone","family":"L\u00f3pez","sequence":"additional","affiliation":[]},{"given":"Aitor","family":"\u00c1lvarez","sequence":"additional","affiliation":[]},{"given":"Egoitz","family":"Rodriguez-Olea","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhao, J., Zhang, W.Q.: Expressive speech-driven facial animation with controllable emotions. In: Proceedings of ICMEW, pp. 387\u2013392. IEEE (2023)","DOI":"10.1109\/ICMEW59549.2023.00073"},{"issue":"1\u20132","key":"9_CR2","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1163\/22134808-00002565","volume":"31","author":"A Alsius","year":"2018","unstructured":"Alsius, A., Par\u00e9, M., Munhall, K.G.: Forty years after hearing lips and seeing voices: the McGurk effect revisited. Multisens. Res. 31(1\u20132), 111\u2013144 (2018)","journal-title":"Multisens. Res."},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Hussen\u00a0Abdelaziz, A., et\u00a0al.: Audiovisual speech synthesis using tacotron2. In: Proceedings of the International Conference on Multimodal Interaction, pp. 503\u2013511 (2021)","DOI":"10.1145\/3462244.3479883"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Yang, K.D., Ranjan, A., et\u00a0al.: Probabilistic speech-driven 3D facial motion synthesis: new benchmarks methods and applications. In: Proceedings of the of CVPR, pp. 27294\u201327303 (2024)","DOI":"10.1109\/CVPR52733.2024.02577"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et\u00a0al.: Media2Face: co-speech facial animation generation with multi-modality guidance. In: ACM SIGGRAPH (2024)","DOI":"10.1145\/3641519.3657413"},{"issue":"4","key":"9_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925984","volume":"35","author":"P Edwards","year":"2016","unstructured":"Edwards, P., et al.: JALI: an animator-centric viseme model for expressive lip synchronization. ACM Trans. Graph. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Thambiraja, B., et\u00a0al.: 3DiFACE: diffusion-based speech-driven 3D facial animation and editing. arXiv preprint arXiv:2312.00870 (2023)","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Xin, R., et al.: Emotion-aware audio-driven face animation via contrastive feature disentanglement. In: Proceedings of the INTERSPEECH 2023, pp. 2728\u20132732 (2023)","DOI":"10.21437\/Interspeech.2023-358"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zhang, X., et\u00a0al.: EmoTalker: emotionally editable talking face generation via diffusion model. In: Proceedings of ICASSP, pp. 8276\u20138280. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447505"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Ravindra, Y., et al.: Stochastic talking face generation using latent distribution matching. In: Proceedings of the Interspeech 2020, pp. 1311\u20131315 (2020)","DOI":"10.21437\/Interspeech.2020-1823"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Villanueva, A., et\u00a0al.: Voice2Face: audio-driven facial and tongue rig animations with cVAEs. In: Computer Graphics Forum, vol.\u00a041, pp. 255\u2013265. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14640"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Xing, J., et\u00a0al.: CodeTalker: speech-driven 3D facial animation with discrete motion prior. In: Proceedings of the CVPR, pp. 12780\u201312790, 2023","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"9_CR13","unstructured":"Zhang, C., et\u00a0al.: Dream-talk: diffusion-based realistic emotional audio-driven method for single image talking face generation. arXiv preprint arXiv:2312.13578 (2023)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Ege, K., Engin, E.: Investigating contributions of speech and facial landmarks for talking head generation. In: Proceedings of the Interspeech 2021, pp. 1624\u20131628 (2021)","DOI":"10.21437\/Interspeech.2021-1585"},{"issue":"5","key":"9_CR15","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1007\/s11263-019-01251-8","volume":"128","author":"K Vougioukas","year":"2020","unstructured":"Vougioukas, K., et al.: Realistic speech-driven facial animation with GANs. Int. J. Comput. Vision 128(5), 1398\u20131413 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR16","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/TASLP.2019.2947741","volume":"28","author":"SE Eskimez","year":"2020","unstructured":"Eskimez, S.E., et al.: Noise-resilient training method for face landmark generation from speech. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 27\u201338 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"9_CR17","doi-asserted-by":"publisher","first-page":"102959","DOI":"10.1016\/j.specom.2023.102959","volume":"153","author":"A Vidal","year":"2023","unstructured":"Vidal, A., Busso, C.: Multimodal attention for lip synthesis using conditional generative adversarial networks. Speech Commun. 153, 102959 (2023)","journal-title":"Speech Commun."},{"issue":"1","key":"9_CR18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.vrih.2023.08.006","volume":"6","author":"L Niu","year":"2024","unstructured":"Niu, L., Xie, W., et al.: Audio2AB: audio-driven collaborative generation of virtual character animation. Virtual Reality Intell. Hardw. 6(1), 56\u201370 (2024)","journal-title":"Virtual Reality Intell. Hardw."},{"key":"9_CR19","unstructured":"V\u00e1squez-Correa, J.C., et al.: Real-time speech-driven avatar animation by predicting facial landmarks and deformation blendshapes. In: Proceedings of ICNLSP 2024, pp. 109\u2013118 (2024)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Tian, G., et\u00a0al.: Audio2face: generating speech\/face animation from single audio with attention-based bidirectional LSTM networks. In: Proceedings of ICMEW, pp. 366\u2013371. IEEE (2019)","DOI":"10.1109\/ICMEW.2019.00069"},{"issue":"6","key":"9_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480484","volume":"40","author":"Y Lu","year":"2021","unstructured":"Lu, Y., et al.: Live speech portraits: real-time photorealistic talking-head animation. ACM Trans. Graph. (TOG) 40(6), 1\u201317 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"9_CR22","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., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"8","key":"9_CR23","first-page":"8615","volume":"35","author":"Y Mao","year":"2022","unstructured":"Mao, Y., Wang, Z., et al.: Task variance regularized multi-task learning. IEEE Trans. Knowl. Data Eng. 35(8), 8615\u20138629 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"4","key":"9_CR24","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., 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":"9_CR25","doi-asserted-by":"crossref","unstructured":"Kefalas, T., et\u00a0al.: Speech-driven facial animation using polynomial fusion of features. In: Proceedings of ICASSP, pp. 3487\u20133491. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054469"},{"key":"9_CR26","unstructured":"Grishchenko, I., et\u00a0al.: Mediapipe blendshape v2 model card (2022)"},{"key":"9_CR27","unstructured":"Gonz\u00e1lez-Docasal, A., et\u00a0al.: EAM: emotional avatar generation for the metaverse. In: SEPLN 2025: International Conference of the Spanish Society for Natural Language Processing (2025)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02548-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:05:01Z","timestamp":1757441101000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02548-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"ISBN":["9783032025470","9783032025487"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02548-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"assertion":[{"value":"22 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Erlangen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.kiv.zcu.cz\/tsd2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}