{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:13:59Z","timestamp":1726038839091},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030275259"},{"type":"electronic","value":"9783030275266"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-27526-6_36","type":"book-chapter","created":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T16:26:01Z","timestamp":1564676761000},"page":"415-426","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Video-Guided Sound Source Separation"],"prefix":"10.1007","author":[{"given":"Junfeng","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Di","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,2]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. arXiv preprint \n                      arXiv:1804.03160\n                      \n                     (2018)","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. arXiv preprint \n                      arXiv:1804.03641\n                      \n                     (2018)","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Segev, D., Schechner, Y.Y., Elad, M.: Example-based cross-modal denoising. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 486\u2013493. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247712"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"36_CR5","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"issue":"10","key":"36_CR6","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1109\/TPAMI.2017.2753232","volume":"40","author":"Y Aytar","year":"2018","unstructured":"Aytar, Y., Castrejon, L., Vondrick, C., Pirsiavash, H., Torralba, A.: Cross-modal scene networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2303\u20132314 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., Hanjalic, A., Shen, H.T.: Adversarial cross-modal retrieval. In: ACM on Multimedia Conference, pp. 154\u2013162 (2017)","DOI":"10.1145\/3123266.3123326"},{"issue":"12","key":"36_CR8","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon, D.R., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Comput. 16(12), 2639\u20132664 (2004)","journal-title":"Neural Comput."},{"key":"36_CR9","unstructured":"Spiertz, M., Gnann, V.: Source-filter based clustering for monaural blind source separation. In: Proceedings of the 12th International Conference on Digital Audio Effects (2009)"},{"issue":"4","key":"36_CR10","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., F\u00e9votte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Ozerov, A., F\u00e9votte, C., Blouet, R., Durrieu, J.L.: Multichannel nonnegative tensor factorization with structured constraints for user-guided audio source separation. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 257\u2013260. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5946389"},{"issue":"3","key":"36_CR12","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"Virtanen, T.: Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Audio Speech Lang. Process. 15(3), 1066\u20131074 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. arXiv preprint \n                      arXiv:1804.01665\n                      \n                     (2018)","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Parekh, S., Essid, S., Ozerov, A., Duong, N.Q., P\u00e9rez, P., Richard, G.: Guiding audio source separation by video object information. In: 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 61\u201365. IEEE (2017)","DOI":"10.1109\/WASPAA.2017.8169995"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Hennequin, R., David, B., Badeau, R.: Score informed audio source separation using a parametric model of non-negative spectrogram. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2011)","DOI":"10.1109\/ICASSP.2011.5946324"},{"issue":"2","key":"36_CR16","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s11265-014-0920-1","volume":"79","author":"L Magoarou Le","year":"2015","unstructured":"Le Magoarou, L., Ozerov, A., Duong, N.Q.: Text-informed audio source separation. Example-based approach using non-negative matrix partial co-factorization. J. Signal Process. Syst. 79(2), 117\u2013131 (2015)","journal-title":"J. Signal Process. Syst."},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Duong, N., Ozerov, A., Chevallier, L., Sirot, J.: An interactive audio source separation framework based on non-negative matrix factorization. In: IEEE International Conference on Acoustics Speech and Signal Processing (2014)","DOI":"10.1109\/ICASSP.2014.6853861"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Barzelay, Z., Schechner, Y.Y.: Harmony in motion. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383344"},{"issue":"5","key":"36_CR19","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1016\/j.camwa.2012.03.077","volume":"64","author":"S Innami","year":"2012","unstructured":"Innami, S., Kasai, H.: NMF-based environmental sound source separation using time-variant gain features. Comput. Math. Appl. 64(5), 1333\u20131342 (2012)","journal-title":"Comput. Math. Appl."},{"issue":"1","key":"36_CR20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2015","unstructured":"Xu, Y., Du, J., Dai, L.R., Lee, C.H.: A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 23(1), 7\u201319 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"issue":"13","key":"36_CR21","doi-asserted-by":"publisher","first-page":"154342","DOI":"10.4108\/eai.14-3-2018.154342","volume":"4","author":"TTH Duong","year":"2018","unstructured":"Duong, T.T.H., Nguyen, P.C., Nguyen, C.Q.: Exploiting nonnegative matrix factorization with mixed group sparsity constraint to separate speech signal from single-channel mixture with unknown ambient noise. EAI Endorsed Trans. Context-Aware Syst. Appl. 4(13), 154342 (2018)","journal-title":"EAI Endorsed Trans. Context-Aware Syst. Appl."},{"issue":"7","key":"36_CR22","first-page":"35","volume":"12","author":"B Arons","year":"1992","unstructured":"Arons, B.: A review of the cocktail party effect. J. Am. Voice I\/O Soc. 12(7), 35\u201350 (1992)","journal-title":"J. Am. Voice I\/O Soc."},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"El Badawy, D., Duong, N.Q., Ozerov, A.: On-the-fly audio source separation. In: 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136. IEEE (2014)","DOI":"10.1109\/MLSP.2014.6958922"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Chen, X., Liu, G., Shi, J., Xu, J., Xu, B.: Distilled binary neural network for monaural speech separation. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2018)","DOI":"10.1109\/IJCNN.2018.8489456"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27526-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T16:44:17Z","timestamp":1564677857000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-27526-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030275259","9783030275266"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27526-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}