{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:29:45Z","timestamp":1766269785328,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377335"},{"type":"electronic","value":"9783030377342"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-37734-2_60","type":"book-chapter","created":{"date-parts":[[2019,12,26]],"date-time":"2019-12-26T19:03:00Z","timestamp":1577386980000},"page":"722-728","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Attention Based Speaker-Independent Audio-Visual Deep Learning Model for Speech Enhancement"],"prefix":"10.1007","author":[{"given":"Zhongbo","family":"Sun","sequence":"first","affiliation":[]},{"given":"Yannan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"key":"60_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). \nhttps:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"60_CR2","doi-asserted-by":"crossref","unstructured":"Cole, F., et al.: Synthesizing normalized faces from facial identity features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.361"},{"issue":"5","key":"60_CR3","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke, M., et al.: 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":"60_CR4","doi-asserted-by":"crossref","unstructured":"El-Solh, A., Cuhadar, A., Goubran, R.A.: Evaluation of speech enhancement techniques for speaker identification in noisy environments. In: Proceedings of ISMW, pp. 235\u2013239 (2007)","DOI":"10.1109\/ISM.Workshops.2007.47"},{"issue":"4","key":"60_CR5","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1145\/3197517.3201357","volume":"37","author":"A Ephrat","year":"2018","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Trans. Graph. (TOG) 37(4), 112 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"60_CR6","doi-asserted-by":"crossref","unstructured":"Gabbay, A., Shamir, A., Peleg, S.: Visual speech enhancement. In: Proceedings of Interspeech 2018, pp. 1170\u20131174 (2018)","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"60_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Li, S., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Kazemi, V., Sullivan, J.: One millisecond face alignment with an ensemble of regression trees. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014","DOI":"10.1109\/CVPR.2014.241"},{"key":"60_CR9","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King, D.E.: Dlib-ml: a machine learning toolkit. J. Mach. Learn. Res. 10, 1755\u20131758 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"60_CR10","volume-title":"Robust Automatic Speech Recognition: A Bridge to Practical Applications","author":"J Li","year":"2015","unstructured":"Li, J., Deng, L., Haeb-Umbach, R., Gong, Y.: Robust Automatic Speech Recognition: A Bridge to Practical Applications, vol. 1. Academic Press, Amsterdam (2015)"},{"issue":"3","key":"60_CR11","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1109\/TASSP.1978.1163086","volume":"26","author":"J Lim","year":"1978","unstructured":"Lim, J., Oppenheim, A.: All-pole modeling of degraded speech. IEEE Trans. ASSP 26(3), 197\u2013210 (1978)","journal-title":"IEEE Trans. ASSP"},{"key":"60_CR12","unstructured":"Ngiam, J., et al.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning, ICML 2011 (2011)"},{"key":"60_CR13","unstructured":"Scalart, P., et al.: Speech enhancement based on a priori signal to noise estimation. In: ICASSP 1996, vol. 2, pp. 629\u2013632 (1996)"},{"issue":"3","key":"60_CR14","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., Steeneken, H.J.: Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"60_CR15","doi-asserted-by":"crossref","unstructured":"Williamson, D.S., Wang, Y., Wang, D.: Complex ratio masking for joint enhancement of magnitude and phase. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472673"},{"key":"60_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). \nhttps:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"60_CR17","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Xu, Y., Du, J., Dai, L.R., Lee, C.H.: An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process. Lett. 21, 65\u201368 (2014)","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37734-2_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T13:14:29Z","timestamp":1580994869000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37734-2_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377335","9783030377342"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37734-2_60","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"171","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":"40","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":"23% - 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":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","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)"}}]}}