{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T15:10:06Z","timestamp":1751814606419,"version":"3.41.0"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-99579-3_22","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"209-214","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LipsID Using 3D Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Miroslav","family":"Hlav\u00e1\u010d","sequence":"first","affiliation":[]},{"given":"Ivan","family":"Gruber","sequence":"additional","affiliation":[]},{"given":"Milo\u0161","family":"\u017delezn\u00fd","sequence":"additional","affiliation":[]},{"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"22_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http:\/\/tensorflow.org\/ . software available from tensorflow.org"},{"key":"22_CR2","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: Lipnet: Sentence-level lipreading. arXiv preprint arXiv:1611.01599 (2016)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Asthana, A., Zafeiriou, S., Cheng, S., Pantic, M.: Incremental face alignment in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1859\u20131866 (2014)","DOI":"10.1109\/CVPR.2014.240"},{"key":"22_CR4","unstructured":"Chollet, F., et al.: Keras: Deep learning library for theano and tensorflow, vol. 7, p. 8 (2015). https:\/\/keras.io\/k"},{"key":"22_CR5","unstructured":"Chung, J.S., Senior, A.W., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. CoRR abs\/1611.05358 (2016). http:\/\/arxiv.org\/abs\/1611.05358"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Chung, J., Zisserman, A.: Lip reading in the wild. In: Asian Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"22_CR7","unstructured":"C\u00edsa\u0159, P., \u017delezn\u1ef3, M., Kr\u0148oul, Z., Kanis, J., Zelinka, J., M\u00fcller, L.: Design and recording of czech speech corpus for audio-visual continuous speech recognition. In: Proceedings of the Auditory-Visual Speech Processing International Conference 2005 (2005)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM (1999)","DOI":"10.1049\/cp:19991218"},{"key":"22_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. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"1","key":"22_CR10","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., Picheny, M.: Speaker adaptation of neural network acoustic models using i-vectors. In: ASRU, pp. 55\u201359 (2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"22_CR12","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T14:40:53Z","timestamp":1751812853000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}