{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:05:09Z","timestamp":1743127509612,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781711"},{"type":"electronic","value":"9783031781728"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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\/978-3-031-78172-8_18","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:48:52Z","timestamp":1733132932000},"page":"271-286","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["StableTalk: Advancing Audio-to-Talking Face Generation with\u00a0Stable Diffusion and Vision Transformer"],"prefix":"10.1007","author":[{"given":"Fatemeh","family":"Nazarieh","sequence":"first","affiliation":[]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1122-0709","authenticated-orcid":false,"given":"Muhammad Awais","family":"Rana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8814-0080","authenticated-orcid":false,"given":"Diptesh","family":"Kanojia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-4249","authenticated-orcid":false,"given":"Zhenhua","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Atito, S., Awais, M., Kittler, J.: GMML is all you need. In: International Conference on Image Processing (2022)","DOI":"10.1109\/ICIP49359.2023.10222150"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bao, J., Chen, D., et\u00a0al.: CVAE-GAN: fine-grained image generation through asymmetric training. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.299"},{"issue":"4","key":"18_CR3","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":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chang, H.C., Chen, H.J., et\u00a0al.: Re-attention is all you need: memory-efficient scene text detection via re-attention on uncertain regions. In: International Conference on Intelligent Robots and Systems (2021)","DOI":"10.1109\/IROS51168.2021.9636510"},{"key":"18_CR5","unstructured":"Chen, L., Cui, G., Kou, Z., Zheng, H., Xu, C.: What comprises a good talking-head video generation?: A survey and benchmark. ArXiv (2020)"},{"key":"18_CR6","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Conference on Neural Information Processing Systems (2021)"},{"key":"18_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kothers: An image is worth 16x16 words: transformers for image recognition at scale. International Conference on Learning Representations (2021)"},{"issue":"11","key":"18_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., et\u00a0al.: Ad-nerf: audio driven neural radiance fields for talking head synthesis. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"18_CR10","unstructured":"Heusel, M., Ramsauer, H., et\u00a0al.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems (2017)"},{"key":"18_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Conference on Neural Information Processing Systems (2020)"},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan, S., Naseer, M., et al.: Transformers in vision: a survey. ACM Comput. Surv. 54, 1\u201341 (2022)","journal-title":"ACM Comput. Surv."},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Khormali, A., Yuan, J.S.: DFDT: an end-to-end deepfake detection framework using vision transformer. Appl. Sci. (2022)","DOI":"10.3390\/app12062953"},{"key":"18_CR14","unstructured":"Kong, Z., Ping, W.: On fast sampling of diffusion probabilistic models (2021)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Liang, J., Zeng, H., Zhang, L.: Details or artifacts: a locally discriminative learning approach to realistic image super-resolution. In: Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00557"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhang, W., et\u00a0al.: Adaptivemix: improving GAN training via feature space shrinkage. In: Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01556"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhang, W., et\u00a0al.: Improving GAN training via feature space shrinkage (2023)","DOI":"10.1109\/CVPR52729.2023.01556"},{"key":"18_CR18","unstructured":"Liu, L., Ren, Y., et\u00a0al.: Pseudo numerical methods for diffusion models on manifolds. In: International Conference on Learning Representations (2022)"},{"key":"18_CR19","unstructured":"Lyu, Z., XU, X., et\u00a0al.: Accelerating diffusion models via early stop of the diffusion process (2022)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Nazarieh, F., Feng, Z., et\u00a0al.: A survey of cross-modal visual content generation. IEEE Trans. Circuits Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3351601"},{"key":"18_CR21","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning (2021)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Prajwal, K.R., 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 International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"18_CR25","unstructured":"Sauer, A., Karras, T., et\u00a0al.: StyleGAN-T: unlocking the power of GANs for fast large-scale text-to-image synthesis (2023)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., et\u00a0al.: wav2vec: unsupervised pre-training for speech recognition. In: Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Sharma, M.: Multi-lingual multi-task speech emotion recognition using wav2vec 2.0. In: International Conference on Acoustics, Speech and Signal Processing (2022)","DOI":"10.1109\/ICASSP43922.2022.9747417"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Shen, S., Zhao, W., et\u00a0al.: Difftalk: crafting diffusion models for generalized audio-driven portraits animation (2023)","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"18_CR29","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhu, J., Li, D., et\u00a0al.: Talking face generation by conditional recurrent adversarial network. In: International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/129"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Stypu\u0142kowski, M., Vougioukas, K., et\u00a0al.: Diffused heads: diffusion models beat GANs on talking-face generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing obama: learning lip sync from audio. ACM Trans. Graph. (2017)","DOI":"10.1145\/3072959.3073640"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A., et\u00a0al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lan, L., et\u00a0al.: Image super-resolution reconstruction based on a generative adversarial network. IEEE Access (2020)","DOI":"10.1109\/ACCESS.2020.3040424"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Xu, X., Kang, Y., et\u00a0al.: Explore wav2vec 2.0 for mispronunciation detection. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-777"},{"key":"18_CR36","unstructured":"Yang, S., Chen, Y., et\u00a0al.: Denoising diffusion step-aware models. In: International Conference on Learning Representations (2024)"},{"key":"18_CR37","unstructured":"Yuanji, W., Jianhua, L., et\u00a0al.: Image quality evaluation based on image weighted separating block peak signal to noise ratio. In: International Conference on Neural Networks and Signal Processing (2003)"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Shysheya, A., et\u00a0al.: Few-shot adversarial learning of realistic neural talking head models. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00955"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., et\u00a0al.: The unreasonable effectiveness of deep features as a perceptual metric. In: Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"18_CR40","unstructured":"Zhou, D., Kang, B., Jin, X., et\u00a0al.: Deepvit: towards deeper vision transformer (2021)"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Han, X., et\u00a0al.: MakeltTalk. ACM Trans. Graph. (2020)","DOI":"10.1145\/3414685.3417774"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78172-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:07:19Z","timestamp":1733134039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78172-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031781711","9783031781728"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78172-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}