{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:53:26Z","timestamp":1740099206908,"version":"3.37.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030000202"},{"type":"electronic","value":"9783030000219"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","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\/978-3-030-00021-9_35","type":"book-chapter","created":{"date-parts":[[2018,9,25]],"date-time":"2018-09-25T11:21:11Z","timestamp":1537874471000},"page":"380-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Aggregated Multimodal Bidirectional Recurrent Model for Audiovisual Speech Recognition"],"prefix":"10.1007","author":[{"given":"Yu","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlin","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongmin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaning","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,26]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Amer, M.R., Siddiquie, B., Khan, S., Divakaran, A., Sawhney, H.: Multimodal fusion using dynamic hybrid models. In: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 556\u2013563. IEEE (2014)","DOI":"10.1109\/WACV.2014.6836053"},{"key":"35_CR2","unstructured":"Amodei, D., et al.: Deep speech 2: End-to-end speech recognition in english and mandarin. In: ICML (2016)"},{"issue":"6","key":"35_CR3","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey, P.K., Hossain, M.A., El Saddik, A., Kankanhalli, M.S.: Multimodal fusion for multimedia analysis: a survey. Multimed. Syst. 16(6), 345\u2013379 (2010)","journal-title":"Multimed. Syst."},{"key":"35_CR4","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http:\/\/www.deeplearningbook.org"},{"key":"35_CR5","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":"8","key":"35_CR6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Hu, D., Li, X., et al.: Temporal multimodal learning in audiovisual speech recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3574\u20133582 (2016)","DOI":"10.1109\/CVPR.2016.389"},{"key":"35_CR8","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Maragos, P., Potamianos, A., Gros, P.: Multimodal Processing and Interaction: Audio, Video, Text, vol. 33. Springer Science & Business Media (2008)","DOI":"10.1007\/978-0-387-76316-3"},{"issue":"2","key":"35_CR10","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"I Matthews","year":"2002","unstructured":"Matthews, I., Cootes, T.F., Bangham, J.A., Cox, S., Harvey, R.: Extraction of visual features for lipreading. IEEE Trans. Pattern Anal. Mach. Intell. 24(2), 198\u2013213 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Mroueh, Y., Marcheret, E., Goel, V.: Deep multimodal learning for audio-visual speech recognition, pp. 2130\u20132134 (2015)","DOI":"10.1109\/ICASSP.2015.7178347"},{"issue":"1","key":"35_CR12","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.neuroimage.2011.07.024","volume":"59","author":"AR Nath","year":"2012","unstructured":"Nath, A.R., Beauchamp, M.S.: A neural basis for interindividual differences in the mcgurk effect, a multisensory speech illusion. NeuroImage 59(1), 781\u2013787 (2012)","journal-title":"NeuroImage"},{"issue":"11","key":"35_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/S1110865702206083","volume":"2002","author":"AV Nefian","year":"2002","unstructured":"Nefian, A.V., Liang, L., Pi, X., Liu, X., Murphy, K.: Dynamic bayesian networks for audio-visual speech recognition. EURASIP J. Adv. Signal Process. 2002(11), 1\u201315 (2002)","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"35_CR14","unstructured":"Ngiam, J., et al.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML-2011), pp. 689\u2013696 (2011)"},{"issue":"4","key":"35_CR15","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","volume":"42","author":"K Noda","year":"2015","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H.G., Ogata, T.: Audio-visual speech recognition using deep learning. Appl. Intell. 42(4), 722\u2013737 (2015)","journal-title":"Appl. Intell."},{"key":"35_CR16","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310\u20131318 (2013)"},{"issue":"4","key":"35_CR17","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/S0893-6080(98)00010-0","volume":"11","author":"L Prechelt","year":"1998","unstructured":"Prechelt, L.: Automatic early stopping using cross validation: quantifying the criteria. Neural Networks 11(4), 761\u2013767 (1998)","journal-title":"Neural Networks"},{"issue":"2","key":"35_CR18","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257\u2013286 (1989)","journal-title":"Proc. IEEE"},{"issue":"11","key":"35_CR19","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"35_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"issue":"1","key":"35_CR21","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"35_CR22","unstructured":"Srivastava, N., Salakhutdinov, R.: Learning representations for multimodal data with deep belief nets. In: International Conference on Machine Learning Workshop, vol. 79 (2012)"},{"key":"35_CR23","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep boltzmann machines. In: Advances in Neural Information Processing Systems, pp. 2222\u20132230 (2012)"},{"key":"35_CR24","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Tamura, S., et al.: Audio-visual speech recognition using deep bottleneck features and high-performance lipreading. In: 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 575\u2013582. IEEE (2015)","DOI":"10.1109\/APSIPA.2015.7415335"},{"key":"35_CR26","first-page":"650","volume-title":"Communications in Computer and Information Science","author":"Chunlin Tian","year":"2017","unstructured":"Tian, C., Yuan, Y., Lu, X.: Deep temporal architecture for audiovisual speech recognition. In: CCF Chinese Conference on Computer Vision, pp. 650\u2013661 (2017)"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, p. I-511. IEEE (2001)","DOI":"10.1109\/CVPR.2001.990517"},{"issue":"7","key":"35_CR28","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/TMM.2009.2030637","volume":"11","author":"G Zhao","year":"2009","unstructured":"Zhao, G., Barnard, M., Pietikainen, M.: Lipreading with local spatiotemporal descriptors. IEEE Trans. Multimed. 11(7), 1254\u20131265 (2009)","journal-title":"IEEE Trans. Multimed."}],"container-title":["Lecture Notes in Computer Science","Cloud Computing and Security"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00021-9_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,24]],"date-time":"2019-10-24T17:00:29Z","timestamp":1571936429000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-00021-9_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030000202","9783030000219"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00021-9_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"ICCCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cloud Computing and Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"incodldos2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icccsconf.org\/icccs2018.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}