{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:19:44Z","timestamp":1783556384947,"version":"3.55.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032222602","type":"print"},{"value":"9783032222619","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\/978-3-032-22261-9_14","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:10:30Z","timestamp":1783555830000},"page":"167-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans"],"prefix":"10.1007","author":[{"given":"Hongbin","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cekai","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijing","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"14_CR1","unstructured":"Anjok07: Ultimate Vocal Remover GUI v5.6. https:\/\/github.com\/Anjok07\/ultimatevocalremovergui (2025). Accessed 20 Mar 2025"},{"key":"14_CR2","doi-asserted-by":"publisher","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187\u2013194. SIGGRAPH \u201999, ACM Press\/Addison-Wesley Publishing Co., USA (1999). https:\/\/doi.org\/10.1145\/311535.311556","DOI":"10.1145\/311535.311556"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: F5-TTS: a fairytaler that fakes fluent and faithful speech with flow matching. arXiv preprint arXiv:2410.06885 (2024)","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"14_CR4","unstructured":"Du, Z., et\u00a0al.: CosyVoice: a scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:2407.05407 (2024)"},{"key":"14_CR5","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv preprint arXiv:2312.10997 (2023)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Guo, Z., Leng, Y., Wu, Y., Zhao, S., Tan, X.: PromptTTS: controllable text-to-speech with text descriptions. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Guo, Z., Xia, L., Yu, Y., Ao, T., Huang, C.: LightRAG: simple and fast retrieval-augmented generation. arXiv preprint arXiv:2410.05779 (2024)","DOI":"10.18653\/v1\/2025.findings-emnlp.568"},{"key":"14_CR8","unstructured":"Hong, S., Lee, S., Moon, H., Lim, H.S.: MIGRATE: cross-lingual adaptation of domain-specific LLMs through code-switching and embedding transfer. In: Proceedings of the 31st International Conference on Computational Linguistics, pp. 9184\u20139193 (2025)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Le, M., et\u00a0al.: Voicebox: text-guided multilingual universal speech generation at scale. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-0618"},{"key":"14_CR11","unstructured":"Lewis, P., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing System, vol. 33, pp. 9459\u20139474 (2020)"},{"key":"14_CR12","unstructured":"Li, J., Yuan, Y., Zhang, Z.: Enhancing LLM factual accuracy with RAG to counter hallucinations: a case study on domain-specific queries in private knowledge-bases. arXiv preprint arXiv:2403.10446 (2024)"},{"key":"14_CR13","doi-asserted-by":"publisher","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) (2017). https:\/\/doi.org\/10.1145\/3130800.3130813","DOI":"10.1145\/3130800.3130813"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Li, Z., Zheng, Z., Wang, L., Liu, Y.: Animatable Gaussians: learning pose-dependent gaussian maps for high-fidelity human avatar modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"14_CR15","doi-asserted-by":"publisher","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6) (2015). https:\/\/doi.org\/10.1145\/2816795.2818013","DOI":"10.1145\/2816795.2818013"},{"issue":"1","key":"14_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021). https:\/\/doi.org\/10.1145\/3503250","journal-title":"Commun. ACM"},{"key":"14_CR17","unstructured":"Nvidia: TensorRT. https:\/\/github.com\/NVIDIA\/TensorRT. Accessed 20 Mar 2025"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Pang, Y., et al.: DPE: disentanglement of pose and expression for general video portrait editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 427\u2013436 (2023)","DOI":"10.1109\/CVPR52729.2023.00049"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive Body Capture: 3D hands, face, and body from a single image. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"14_CR20","unstructured":"Picovoice: Porcupine. https:\/\/github.com\/Picovoice\/porcupine. Accessed 26 Mar 2025"},{"key":"14_CR21","unstructured":"Qwen Team: Qwen2.5: a party of foundation models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/ (2024)"},{"key":"14_CR22","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"14_CR24","unstructured":"RVC-Boss: GPT-SoVITS. https:\/\/github.com\/RVC-Boss\/GPT-SoVITS. Accessed 20 Mar 2025"},{"issue":"4","key":"14_CR25","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1162\/pres.16.4.337","volume":"16","author":"J Seyama","year":"2007","unstructured":"Seyama, J., Nagayama, R.S.: The uncanny valley: effect of realism on the impression of artificial human faces. Presence 16(4), 337\u2013351 (2007). https:\/\/doi.org\/10.1162\/pres.16.4.337","journal-title":"Presence"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Shao, Z., et al.: DEGAS: detailed expressions on full-body gaussian avatars. In: Proceedings of the International Conference on 3D Vision (3DV) (2025)","DOI":"10.1109\/3DV66043.2025.00143"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Shao, Z., et al.: SplattingAvatar: realistic real-time human avatars with mesh-embedded gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"14_CR28","unstructured":"Shen, K., et al.: NaturalSpeech 2: latent diffusion models are natural and zero-shot speech and singing synthesizers. In: International Conference on Learning Representations, pp. 1\u201325 (2024)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Thambiraja, B., Habibie, I., Aliakbarian, S., Cosker, D., Theobalt, C., Thies, J.: Imitator: personalized speech-driven 3D facial animation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20621\u201320631 (2023)","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"14_CR30","unstructured":"Wang, C., et\u00a0al.: Survey on factuality in large language models: knowledge, retrieval and domain-specificity. arXiv preprint arXiv:2310.07521 (2023)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Chen, Z., Yu, T., Ma, C., Li, L., Liu, Y.: FaceVerse: a fine-grained and detail-controllable 3D face morphable model from a hybrid dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"14_CR32","unstructured":"Wang, S., et al.: DomainRAG: a Chinese benchmark for evaluating domain-specific retrieval-augmented generation. arXiv preprint arXiv:2406.05654 (2024)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Xie, T., Rong, Y., Zhang, P., Liu, L.: Towards controllable speech synthesis in the era of large language models: a survey. arXiv preprint arXiv:2412.06602 (2024)","DOI":"10.18653\/v1\/2025.emnlp-main.40"},{"key":"14_CR34","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.1109\/TASLP.2024.3402088","volume":"32","author":"D Yang","year":"2024","unstructured":"Yang, D., Liu, S., Huang, R., Weng, C., Meng, H.: InstructTTS: modelling expressive TTS in discrete latent space with natural language style prompt. IEEE\/ACM Trans. Audio, Speech Lang. Process. 32, 2913\u20132925 (2024)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process."},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhang, M., Wei, D., Guo, J.: SRAG: speech retrieval augmented generation for spoken language understanding. In: 2024 IEEE 2nd International Conference on Control, Electronics and Computer Technology (ICCECT), pp. 370\u2013374. IEEE (2024)","DOI":"10.1109\/ICCECT60629.2024.10546001"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: FaceScape: a large-scale high quality 3D face dataset and detailed riggable 3D face prediction. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Yifan, W., Wetzstein, G., Black, M.J., Hilliges, O.: PointAvatar: deformable point-based head avatars from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02017"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-22261-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:10:34Z","timestamp":1783555834000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-22261-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032222602","9783032222619"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-22261-9_14","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":"2 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","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":"14 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi25","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}