{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:04:54Z","timestamp":1753272294903,"version":"3.40.5"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602758"},{"type":"electronic","value":"9783030602765"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_18","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"176-183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Lipreading with LipsID"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-930X","authenticated-orcid":false,"given":"Miroslav","family":"Hlav\u00e1\u010d","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2333-433X","authenticated-orcid":false,"given":"Ivan","family":"Gruber","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1695-4370","authenticated-orcid":false,"given":"Milo\u0161","family":"\u017delezn\u00fd","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3424-652X","authenticated-orcid":false,"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"18_CR1","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: LRS3-TED: a large-scale dataset for visual speech recognition (2018). arXiv preprint arXiv:1809.00496"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"18_CR3","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., De Freitas, N.: Lipet: End-to-end sentence-level lipreading (2016). arXiv preprint arXiv:1611.01599"},{"key":"18_CR4","unstructured":"Chollet, F.: Keras: GitHub repository (2015)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3444\u20133453. IEEE (2017)","DOI":"10.1109\/CVPR.2017.367"},{"issue":"5","key":"18_CR6","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"18_CR7","unstructured":"Cootes, T.F., Cristopher J.T.: Statistical models of appearance for computer vision (2004)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"18_CR9","doi-asserted-by":"crossref","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 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"18_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-319-99579-3_22","volume-title":"Speech and Computer","author":"M Hlav\u00e1\u010d","year":"2018","unstructured":"Hlav\u00e1\u010d, M., Gruber, I., \u017delezn\u00fd, M., Karpov, A.: LipsID using 3D convolutional neural networks. In: Karpov, A., Jokisch, O., Potapova, R. (eds.) SPECOM 2018. LNCS (LNAI), vol. 11096, pp. 209\u2013214. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99579-3_22"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Karafi\u00e1t, M., Burget, L., Mat\u011bjka, P., Glembek, O., \u010cernock\u00fd, J.: iVector-based discriminative adaptation for automatic speech recognition. In: 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, Waikoloa, HI, pp. 152\u2013157 (2011). https:\/\/doi.org\/10.1109\/ASRU.2011.6163922","DOI":"10.1109\/ASRU.2011.6163922"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Sterpu G., Saam C., Harte N.: How to teach DNNs to pay attention to the visual modality in speech recognition. In: IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.2980436","DOI":"10.1109\/TASLP.2020.2980436"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Hlav\u00e1\u010d, M.: Automated Lipreading with LipsID Features. PhD Thesis, University of West Bohemia, (2019)","DOI":"10.1007\/978-3-030-60276-5_18"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Sterpu, G., Saam, C., Harte, N.: Attention-based audio-visual fusion for robust automatic speech recognition. In: 2018 International Conference on Multimodal Interaction (ICMI 2018) (2018). https:\/\/doi.org\/10.1145\/3242969.3243014","DOI":"10.1145\/3242969.3243014"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Harte, N., Gillen, E.: TCD-TIMIT: an Audio-Visual Corpus of Continuous Speech. In: IEEE Transactions on Multimedia, pp. 603\u2013615 (2015). https:\/\/doi.org\/10.1109\/TMM.2015.2407694","DOI":"10.1109\/TMM.2015.2407694"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T02:40:30Z","timestamp":1669084830000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"160","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"65","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}