{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:00Z","timestamp":1785649620182,"version":"3.56.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032319197","type":"print"},{"value":"9783032319203","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31920-3_16","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:25:49Z","timestamp":1785648349000},"page":"232-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MuS: Multilingual Synergy with\u00a0Shared Representations for\u00a0Visual Speech Recognition"],"prefix":"10.1007","author":[{"given":"Yuheng","family":"Fan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: Deep lip reading: a comparison of models and an online application (2018). arXiv:1806.06053 arXiv preprint","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, Y.J., Park, J., Park, S., Choi, J., Kim, K.E.: SyncVSR: data-efficient visual speech recognition with end-to-end crossmodal audio token synchronization. arXiv preprint arXiv:2406.12233 (2024)","DOI":"10.21437\/Interspeech.2024-432"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Anwar, M., Shi, B., Goswami, V., Hsu, W.N., Pino, J., Wang, C.: MuAVIC: a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation (2023). arXiv:2303.00628 arXiv preprint","DOI":"10.21437\/Interspeech.2023-2279"},{"issue":"6027","key":"16_CR4","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1126\/science.1199295","volume":"332","author":"QD Atkinson","year":"2011","unstructured":"Atkinson, Q.D.: Phonemic diversity supports a serial founder effect model of language expansion from Africa. Science 332(6027), 346\u2013349 (2011)","journal-title":"Science"},{"key":"16_CR5","unstructured":"Cappellazzo, U., et al.: MOME: mixture of matryoshka experts for audio-visual speech recognition (2025). arXiv:2510.04136 arXiv preprint"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Cappellazzo, U., Liu, X., Ma, P., Petridis, S., Pantic, M.: Omni-AVSR: towards unified multimodal speech recognition with large language models (2025). arXiv:2511.07253 arXiv preprint","DOI":"10.1109\/ICASSP55912.2026.11461431"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: MAESTRO: matched speech text representations through modality matching (2022). arXiv:2204.03409 arXiv preprint","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chien, J.T., Liu, P.Y.: Aligning speech-text representations via contrastive modality translation. IEEE Trans. Audio Speech Lang. Process. 33 (2025)","DOI":"10.1109\/TASLPRO.2025.3603910"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ICML \u201806, Association for Computing Machinery, New York, NY, USA (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"16_CR10","unstructured":"He, C., Li, W., Jin, Z., Xu, C., Wang, B., Lin, D.: OpenDataLab: empowering general artificial intelligence with open datasets (2024). https:\/\/arxiv.org\/abs\/2407.13773"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Kim, M., Yeo, J.H., Choi, J., Ro, Y.M.: Lip reading for low-resource languages by learning and combining general speech knowledge and language-specific knowledge. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15359\u201315371 (2023)","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Kim, M., Yeo, J., Park, S.J., Rha, H., Ro, Y.M.: Efficient training for multilingual visual speech recognition: pre-training with discretized visual speech representation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 1311\u20131320 (2024)","DOI":"10.1145\/3664647.3681221"},{"key":"16_CR13","unstructured":"Kit Khinn\u00a0Teng, M., Zhang, H., Saitoh, T.: Phoneme-level visual speech recognition via point-visual fusion and language model reconstruction. arXiv e-prints pp. arXiv\u20132507 (2025)"},{"key":"16_CR14","unstructured":"Ladgfoged, P.: A Course in Phonetics. Heinle & Heinle (2001)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Laux, H., Mededovic, E., Hallawa, A., Martin, L., Peine, A., Schmeink, A.: Litevsr: Efficient visual speech recognition by learning from speech representations of unlabeled data. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10391\u201310395. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448428"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Liu, A.H., Hsu, W.N., Auli, M., Baevski, A.: Towards end-to-end unsupervised speech recognition. In: 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 221\u2013228. IEEE (2023)","DOI":"10.1109\/SLT54892.2023.10023187"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, X., Chen, C., Guo, L., Li, L., Wang, D.: AlignVSR: audio-visual cross-modal alignment for visual speech recognition. arXiv preprint arXiv:2410.16438 (2024)","DOI":"10.1145\/3784833.3784842"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Luo, M., Yang, S., Chen, X., Liu, Z., Shan, S.: Synchronous bidirectional learning for multilingual lip reading (2020). arXiv:2005.03846 arXiv preprint","DOI":"10.5244\/C.34.172"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Ma, P., Haliassos, A., Fernandez-Lopez, A., Chen, H., Petridis, S., Pantic, M.: Auto-AVSR: audio-visual speech recognition with automatic labels. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096889","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Ma, P., Petridis, S., Pantic, M.: End-to-end audio-visual speech recognition with conformers. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7613\u20137617. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"issue":"11","key":"16_CR21","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. Nat. Mach. Intell. 4(11), 930\u2013939 (2022)","journal-title":"Nat. Mach. Intell."},{"key":"16_CR22","doi-asserted-by":"publisher","first-page":"30811","DOI":"10.52202\/079017-0970","volume":"37","author":"G Penedo","year":"2024","unstructured":"Penedo, G., et al.: The fineweb datasets: decanting the web for the finest text data at scale. Adv. Neural. Inf. Process. Syst. 37, 30811\u201330849 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: ConFormer: local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 367\u2013376 (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Salesky, E., et al.: The multilingual TEDX corpus for speech recognition and translation (2021). https:\/\/arxiv.org\/abs\/2102.01757","DOI":"10.21437\/Interspeech.2021-11"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Shao, H., Liu, B., Wang, W., Gong, X., Qian, Y.: DQ-Whisper: joint distillation and quantization for efficient multilingual speech recognition. In: 2024 IEEE Spoken Language Technology Workshop (SLT), pp. 240\u2013246. IEEE (2024)","DOI":"10.1109\/SLT61566.2024.10832149"},{"key":"16_CR26","unstructured":"Shi, B., Hsu, W.N., Lakhotia, K., Mohamed, A.: Learning audio-visual speech representation by masked multimodal cluster prediction (2022). arXiv:2201.02184 arXiv preprint"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Chung, S., Senior, J., Vinyals, A., Zisserman, O., A.: Lip reading sentences in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6447\u20136456 (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"16_CR28","unstructured":"Xia, B., Yang, S., Shan, S., Chen, X.: UniLip: learning visual-textual mapping with uni-modal data for lip reading. In: BMVC, pp. 190\u2013191 (2023)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the wild. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp.\u00a01\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756582"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Yeo, J.H., Kim, M., Kim, C.W., Petridis, S., Ro, Y.M.: Zero-AVSR: zero-shot audio-visual speech recognition with LLMs by learning language-agnostic speech representations. arXiv preprint arXiv:2503.06273 (2025)","DOI":"10.1109\/ICCV51701.2025.00630"},{"key":"16_CR31","unstructured":"Zellinger, W., Grubinger, T., Lughofer, E., Natschl\u00e4ger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning (2017). arXiv:1702.08811 arXiv preprint"},{"key":"16_CR32","unstructured":"Zhang, J.X., Wan, G., Li, J., Gao, J.: Adapting speech foundation models with large language models for unified speech recognition (2025). arXiv:2510.22961 arXiv preprint"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, S., Shan, S., Chen, X.: ES3: evolving self-supervised learning of robust audio-visual speech representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 27069\u201327079 (2024)","DOI":"10.1109\/CVPR52733.2024.02556"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: MMSpeech: multi-modal multi-task encoder-decoder pre-training for speech recognition. In: Proceedings of Interspeech 2023, pp. 4943\u20134947 (2023)","DOI":"10.21437\/Interspeech.2023-791"},{"key":"16_CR35","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1109\/TMM.2023.3275873","volume":"26","author":"Q Zhu","year":"2023","unstructured":"Zhu, Q., et al.: VATLM: visual-audio-text pre-training with unified masked prediction for speech representation learning. IEEE Trans. Multimedia 26, 1055\u20131064 (2023)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31920-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:25:52Z","timestamp":1785648352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31920-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032319197","9783032319203"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31920-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","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":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","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":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}