{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T11:03:51Z","timestamp":1768907031854,"version":"3.49.0"},"reference-count":10,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11704-024-3787-8","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T23:52:21Z","timestamp":1719273141000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio-guided self-supervised learning for disentangled visual speech representations"],"prefix":"10.1007","volume":"18","author":[{"given":"Dalu","family":"Feng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,25]]},"reference":[{"key":"3787_CR1","unstructured":"Shi B, Hsu W N, Lakhotia K, Mohamed A. Learning audio-visual speech representation by masked multimodal cluster prediction. In: Proceedings of the 10th International Conference on Learning Representations. 2022"},{"key":"3787_CR2","unstructured":"Hsu W N, Shi B. u-HuBERT: unified mixed-modal speech pretraining and zero-shot transfer to unlabeled modality. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1538"},{"key":"3787_CR3","doi-asserted-by":"crossref","unstructured":"Stafylakis T, Tzimiropoulos G. Combining residual networks with LSTMs for lipreading. In: Proceedings of the 18th Annual Conference of the International Speech Communication Association. 2017, 3652\u20133656","DOI":"10.21437\/Interspeech.2017-85"},{"key":"3787_CR4","doi-asserted-by":"crossref","unstructured":"Ma P, Martinez B, Petridis S, Pantic M. Towards practical lipreading with distilled and efficient models. In: Proceedings of 2021 IEEE International Conference on Acoustics, Speech and Signal Processing. 2021, 7608\u20137612","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"3787_CR5","doi-asserted-by":"crossref","unstructured":"Ma P, Wang Y, Shen J, Petridis S, Pantic M. Lip-reading with densely connected temporal convolutional networks. In: Proceedings of 2021 IEEE Winter Conference on Applications of Computer Vision. 2021, 2856\u20132865","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"3787_CR6","doi-asserted-by":"crossref","unstructured":"Koumparoulis A, Potamianos G. Accurate and resource-efficient lipreading with efficientnetv2 and transformers. In: Proceedings of 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. 2022, 8467\u20138471","DOI":"10.1109\/ICASSP43922.2022.9747729"},{"key":"3787_CR7","doi-asserted-by":"crossref","unstructured":"Ma P, Petridis S, Pantic M. End-to-end audio-visual speech recognition with conformers. In: Proceedings of 2021 IEEE International Conference on Acoustics, Speech and Signal Processing. 2021, 7613\u20137617","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"issue":"11","key":"3787_CR8","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1038\/s42256-022-00550-z","volume":"4","author":"P Ma","year":"2022","unstructured":"Ma P, Petridis S, Pantic M. Visual speech recognition for multiple languages in the wild. Nature Machine Intelligence, 2022, 4(11): 930\u2013939","journal-title":"Nature Machine Intelligence"},{"key":"3787_CR9","doi-asserted-by":"crossref","unstructured":"Ma P, Haliassos A, Fernandez-Lopez A, Chen H, Petridis S, Pantic M. Auto-AVSR: audio-visual speech recognition with automatic labels. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. 2023, 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"issue":"12","key":"3787_CR10","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1631\/FITEE.2100463","volume":"22","author":"Y Yang","year":"2021","unstructured":"Yang Y, Zhuang Y, Pan Y. Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies. Frontiers of Information Technology & Electronic Engineering, 2021, 22(12): 1551\u20131558","journal-title":"Frontiers of Information Technology & Electronic Engineering"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-3787-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-024-3787-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-3787-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:33:04Z","timestamp":1768854784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-024-3787-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":10,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3787"],"URL":"https:\/\/doi.org\/10.1007\/s11704-024-3787-8","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,25]]},"assertion":[{"value":"1 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Competing interests\n                      The authors declare that they have no competing interests or financial conflicts to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"186353"}}