{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T04:55:14Z","timestamp":1782622514340,"version":"3.54.5"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Xi'an Polytechnic University Graduate Innovation Fund","award":["chx2025027"],"award-info":[{"award-number":["chx2025027"]}]},{"name":"the 2024 Youth Innovation Team Project under the Scientific Research Program of Shaanxi Provincial Department of Education","award":["24JP069"],"award-info":[{"award-number":["24JP069"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04201-3","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T12:52:22Z","timestamp":1766148742000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Application of the fast diffusion model ST-diffusion in multi-modal lip-to-speech generation"],"prefix":"10.1007","volume":"42","author":[{"given":"Qiong","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"4201_CR1","doi-asserted-by":"publisher","unstructured":"Hegde, S.B., Prajwal, K.R., Mukhopadhyay, R., et al.: Lip-to-speech synthesis for arbitrary speakers in the wild. In: Proceedings of the 30th ACM international conference on multimedia, pp. 6250\u20136258 (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.00642","DOI":"10.48550\/arXiv.2209.00642"},{"issue":"9","key":"4201_CR2","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"F-A 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."},{"key":"4201_CR3","doi-asserted-by":"publisher","first-page":"4525","DOI":"10.1038\/s41598-024-55248-6","volume":"14","author":"Q Yang","year":"2024","unstructured":"Yang, Q., Bai, Y., Liu, F., et al.: Integrated visual transformer and flash attention for lip-to-speech generation GAN. Sci. Rep. 14, 4525 (2024). https:\/\/doi.org\/10.1038\/s41598-024-55248-6","journal-title":"Sci. Rep."},{"key":"4201_CR4","doi-asserted-by":"publisher","unstructured":"Li, J., Zhang, J., Bai, X., et al.: Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7568\u20137578 (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.09323","DOI":"10.48550\/arXiv.2307.09323"},{"key":"4201_CR5","doi-asserted-by":"publisher","unstructured":"Gao, S., Zhou, P., Cheng, M.M., et al.: MDTv2: masked diffusion transformer is a strong image synthesizer. arXiv preprint arXiv:2303.14389 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.14389","DOI":"10.48550\/arXiv.2303.14389"},{"key":"4201_CR6","doi-asserted-by":"publisher","unstructured":"Yu, J., Zhang, S.X., Wu, J., et al.: Audio-visual recognition of overlapped speech for the LRS2 dataset. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp. 6984\u20136988 (2020). https:\/\/doi.org\/10.48550\/arXiv.2001.01656","DOI":"10.48550\/arXiv.2001.01656"},{"key":"4201_CR7","doi-asserted-by":"publisher","unstructured":"Chen, W., Tan, X., Xia, Y., et al.: DualLip: a system for joint lip reading and generation. In: Proceedings of the 28th ACM international conference on multimedia, pp. 1985\u20131993 (2020). https:\/\/doi.org\/10.48550\/arXiv.2009.05784","DOI":"10.48550\/arXiv.2009.05784"},{"key":"4201_CR8","doi-asserted-by":"crossref","unstructured":"Dixit, A., Sethi, P., Garg, P., et al.: CNN based lip-reading system for visual input: a review. AIP Conf. Proc.  3121(1), 020001 (2024). https:\/\/www.researchgate.net\/publication\/382274409","DOI":"10.1063\/5.0221717"},{"key":"4201_CR9","unstructured":"Kim, M., Hong, J., Ro, Y.M.: Lip to speech synthesis with visual context attentional GAN. In: Advances in neural information processing systems, vol. 34, pp. 2758\u20132770 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/16437d40c29a1a7b1e78143c9c38f289-Abstract.html"},{"key":"4201_CR10","doi-asserted-by":"publisher","unstructured":"Yemini, Y., Shamsian, A., Bracha, L., et al.: LipVoicer: generating speech from silent videos guided by lip reading. arXiv preprint arXiv:2306.03258 (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.03258","DOI":"10.48550\/arXiv.2306.03258"},{"key":"4201_CR11","doi-asserted-by":"publisher","unstructured":"Kong, Z., Ping, W., Huang, J., et al.: DiffWave: a versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 (2020). https:\/\/doi.org\/10.48550\/arXiv.2009.09761","DOI":"10.48550\/arXiv.2009.09761"},{"key":"4201_CR12","doi-asserted-by":"crossref","unstructured":"Grassucci, E., Marinoni, C., Rodriguez, A., et al.: Diffusion models for audio semantic communication. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp. 13136\u201313140 (2024). https:\/\/ieeexplore.ieee.org\/abstract\/document\/10447612","DOI":"10.1109\/ICASSP48485.2024.10447612"},{"key":"4201_CR13","doi-asserted-by":"crossref","unstructured":"Leng, Y., Chen, Z., Guo, J., et al.: BinauralGrad: a two-stage conditional diffusion probabilistic model for binaural audio synthesis. In: Advances in neural information processing systems, vol. 35, pp. 23689\u201323700 (2022). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/95f03faf3763e1b1ce2c3de62da8f090-Abstract-Conference.html","DOI":"10.52202\/068431-1721"},{"key":"4201_CR14","doi-asserted-by":"publisher","unstructured":"Moliner, E., Lehtinen, J., V\u00e4lim\u00e4ki, V.: Solving audio inverse problems with a diffusion model. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp. 1\u20135 (2023). https:\/\/doi.org\/10.48550\/arXiv.2210.15228","DOI":"10.48550\/arXiv.2210.15228"},{"issue":"3","key":"4201_CR15","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1109\/TCSVT.2021.3079897","volume":"32","author":"S Liu","year":"2021","unstructured":"Liu, S., Li, S., Cheng, H.: Towards an end-to-end visual-to-raw-audio generation with GAN. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1299\u20131312 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4201_CR16","doi-asserted-by":"publisher","first-page":"4224","DOI":"10.1007\/s00034-025-03010-2","volume":"44","author":"C Jannu","year":"2025","unstructured":"Jannu, C., Burra, M., Vanambathina, S.D., et al.: Single channel speech enhancement using a complex dual-path multi axial transformer with frequency prompt. Circuits Syst. Signal Process. 44, 4224\u20134257 (2025). https:\/\/doi.org\/10.1007\/s00034-025-03010-2","journal-title":"Circuits Syst. Signal Process."},{"key":"4201_CR17","doi-asserted-by":"publisher","unstructured":"Nakadai, K., Hidai, K., Okuno, H.G., Kitano, H.: Real-time speaker localization and speech separation by audio-visual integration. In: Proceedings of the IEEE international conference on robotics and Aautomation, vol. 1, pp. 1043\u20131049 (2002). https:\/\/doi.org\/10.1109\/ROBOT.2002.1013493","DOI":"10.1109\/ROBOT.2002.1013493"},{"key":"4201_CR18","doi-asserted-by":"publisher","first-page":"7467","DOI":"10.1007\/s00034-023-02455-7","volume":"42","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: Multi-stage progressive learning-based speech enhancement using time\u2013frequency attentive squeezed temporal convolutional networks. Circuits Syst. Signal Process. 42, 7467\u20137493 (2023). https:\/\/doi.org\/10.1007\/s00034-023-02455-7","journal-title":"Circuits Syst. Signal Process."},{"issue":"4","key":"4201_CR19","doi-asserted-by":"publisher","first-page":"7899","DOI":"10.3233\/JIFS-233312","volume":"46","author":"V Parisae","year":"2024","unstructured":"Parisae, V., Bhavanam, S.N.: Multi scale encoder-decoder network with time frequency attention and S-TCN for single channel speech enhancement. J. Intell. Fuzzy Syst. 46(4), 7899\u20137915 (2024). https:\/\/doi.org\/10.3233\/JIFS-233312","journal-title":"J. Intell. Fuzzy Syst."},{"key":"4201_CR20","doi-asserted-by":"publisher","unstructured":"Vanambathina, S.D., Nandyala, S., Jannu, C., et al.: Speech enhancement using U-Net-based progressive learning with squeeze-TCN. In: Advances in Distributed Computing and Machine Learning, pp. 399\u2013411 (2024). https:\/\/doi.org\/10.1007\/978-981-97-3523-5_31","DOI":"10.1007\/978-981-97-3523-5_31"},{"issue":"4","key":"4201_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/coin.70016","volume":"41","author":"C Jannu","year":"2025","unstructured":"Jannu, C., Burra, M., Vanambathina, S.D., Parisae, V.: Real-time single channel speech enhancement using triple attention and stacked squeeze-TCN. Comput. Intell. 41(4), 1\u201323 (2025). https:\/\/doi.org\/10.1111\/coin.70016","journal-title":"Comput. Intell."},{"key":"4201_CR22","doi-asserted-by":"crossref","unstructured":"Karthikeya, A., Kumar, A.A., Manicharan, C., et al.: Enhanced deep learning approach for text to image conversion using lip movements. In: Proceedings of the 4th international conference on innovative practices in technology and management, pp. 1\u20135 (2024). https:\/\/ieeexplore.ieee.org\/abstract\/document\/10563385","DOI":"10.1109\/ICIPTM59628.2024.10563385"},{"key":"4201_CR23","doi-asserted-by":"publisher","unstructured":"Mukhopadhyay, S., Suri, S., Gadde, R.T., et al.: 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). https:\/\/doi.org\/10.48550\/arXiv.2308.09716","DOI":"10.48550\/arXiv.2308.09716"},{"key":"4201_CR24","doi-asserted-by":"crossref","unstructured":"Gomes, R., Rozario, P., Adhikari, N.: Deep learning optimization in remote sensing image segmentation using dilated convolutions and ShuffleNet. In: Proceedings of the IEEE on international conference electro information technology, pp. 244\u2013249 (2021). https:\/\/ieeexplore.ieee.org\/abstract\/document\/9491910","DOI":"10.1109\/EIT51626.2021.9491910"},{"key":"4201_CR25","doi-asserted-by":"publisher","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017). https:\/\/doi.org\/10.48550\/arXiv.1703.07737","DOI":"10.48550\/arXiv.1703.07737"},{"key":"4201_CR26","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in neural information processing systems, vol. 33, pp. 6840\u20136851 (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"4201_CR27","doi-asserted-by":"publisher","unstructured":"Sutanto, A.R., Kang, D.K.: A novel diminish smooth L1 loss model with generative adversarial network. In: Proceedings of the international conference on intelligent human-computer interaction, pp. 361\u2013368 (2021). https:\/\/doi.org\/10.1007\/978-3-030-68449-5_36","DOI":"10.1007\/978-3-030-68449-5_36"},{"key":"4201_CR28","doi-asserted-by":"crossref","unstructured":"Barz, B., Denzler, J.: Deep learning on small datasets without pre-training using cosine loss. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 1371\u20131380 (2020). https:\/\/openaccess.thecvf.com\/content_WACV_2020\/html\/Barz_Deep_Learning_on_Small_Datasets_without_Pre-Training_using_Cosine_Loss_WACV_2020_paper.html","DOI":"10.1109\/WACV45572.2020.9093286"},{"issue":"10","key":"4201_CR29","first-page":"410","volume":"9","author":"U Ruby","year":"2020","unstructured":"Ruby, U., Yendapalli, V.: Binary cross entropy with deep learning technique for image classification. Int. J. Adv. Trends Comput. Sci. Eng. 9(10), 410\u2013417 (2020)","journal-title":"Int. J. Adv. Trends Comput. Sci. Eng."},{"key":"4201_CR30","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., et al.: LipNet: sentence-level lipreading. arXiv preprint arXiv:1611.01599 (2016). https:\/\/innovators-guide.ch\/wp-content\/uploads\/2016\/11\/2016-Assael_Shillingford_LipNet.pdf"},{"key":"4201_CR31","doi-asserted-by":"crossref","unstructured":"Akbari, H., Arora, H., Cao, L., et al.: Lip2AudSpec: speech reconstruction from silent lip movements video. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp. 2516\u20132520 (2018). https:\/\/ieeexplore.ieee.org\/abstract\/document\/8461856","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"4201_CR32","doi-asserted-by":"crossref","unstructured":"Xu, K., Li, D., Cassimatis, N., et al.: LCANet: end-to-end lipreading with cascaded attention-CTC. In: Proceedings of the 13th IEEE international conference on automatic face & gesture recognition, pp. 548\u2013555 (2018). https:\/\/ieeexplore.ieee.org\/abstract\/document\/8373881","DOI":"10.1109\/FG.2018.00088"},{"key":"4201_CR33","doi-asserted-by":"crossref","unstructured":"Ephrat, A., Peleg, S.: Vid2speech: speech reconstruction from silent video. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp. 5095\u20135099 (2017). https:\/\/ieeexplore.ieee.org\/abstract\/document\/7953127","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"4201_CR34","doi-asserted-by":"crossref","unstructured":"Prajwal, K.R., Mukhopadhyay, R., Namboodiri, V.P., et al.: Learning individual speaking styles for accurate lip to speech synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13796\u201313805 (2020). https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Prajwal_Learning_Individual_Speaking_Styles_for_Accurate_Lip_to_Speech_Synthesis_CVPR_2020_paper.html","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"4201_CR35","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King, D.E.: Dlib-ML: a machine learning toolkit. J. Mach. Learn. Res. 10, 1755\u20131758 (2009)","journal-title":"J. Mach. Learn. Res."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04201-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04201-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04201-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:03:34Z","timestamp":1772629414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04201-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4201"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04201-3","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"28 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}},{"value":"In the writing process, we used Al tools primarily to streamline the reading logic of the article and polish the writing grammar, aiming to improve the readability of the article and make it easier for readers to understand.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration of generative Al and AI-assisted technologies in the writing process"}}],"article-number":"81"}}