{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:05:51Z","timestamp":1767773151043,"version":"3.37.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030057152"},{"type":"electronic","value":"9783030057169"}],"license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"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\/978-3-030-05716-9_13","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:17:32Z","timestamp":1544451452000},"page":"157-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-channel Convolutional Neural Networks with Multi-level Feature Fusion for Environmental Sound Classification"],"prefix":"10.1007","author":[{"given":"Dading","family":"Chong","sequence":"first","affiliation":[]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0","volume-title":"Computational Analysis of Sound Scenes and Events","author":"T Virtanen","year":"2018","unstructured":"Virtanen, T., Plumbley, M.D., Ellis, D.: Computational Analysis of Sound Scenes and Events. Springer, Heidelberg (2018). \nhttps:\/\/doi.org\/10.1007\/978-3-319-63450-0"},{"key":"13_CR2","doi-asserted-by":"crossref","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","volume":"112","author":"V Boddapati","year":"2017","unstructured":"Boddapati, V., Petef, A., Rasmusson, J., Lundberg, L.: Classifying environmental sounds using image recognition networks. Proc. Comput. Sci. 112, 2048\u20132056 (2017)","journal-title":"Proc. Comput. Sci."},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"13_CR4","unstructured":"Vacher, M., Serignat, J.-F., Chaillol, S.: Sound classification in a smart room environment: an approach using GMM and HMM methods. In: The 4th IEEE Conference on Speech Technology and Human-Computer Dialogue (SpeD 2007), Publishing House of the Romanian Academy (Bucharest), pp. 135\u2013146 (2007)"},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/978-3-642-14989-4_5","volume-title":"Advances in Multimedia and Network Information System Technologies","author":"K \u0141opatka","year":"2010","unstructured":"\u0141opatka, K., Zwan, P., Czy\u017cewski, A.: Dangerous sound event recognition using support vector machine classifiers. In: Nguyen, N.T., Zgrzywa, A., Czy\u017cewski, A. (eds.) Advances in Multimedia and Network Information System Technologies, pp. 49\u201357. Springer, Heidelberg (2010). \nhttps:\/\/doi.org\/10.1007\/978-3-642-14989-4_5"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Su, F., Yang, L., Lu, T., Wang, G.: Environmental sound classification for scene recognition using local discriminant bases and HMM. In: Proceedings of the 19th ACM International Conference on Multimedia, pp. 1389\u20131392. ACM (2011)","DOI":"10.1145\/2072298.2072022"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Saki, F., Kehtarnavaz, N.: Background noise classification using random forest tree classifier for cochlear implant applications. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3591\u20133595. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854270"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Mohamed, A.-R., Kingsbury, B., Ramabhadran, B.: Deep convolutional neural networks for LVCSR. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8614\u20138618. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"13_CR9","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid, O., Mohamed, A.-R., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22, 1533\u20131545 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"13_CR10","unstructured":"Kong, Q., Sobieraj, I., Wang, W., Plumbley, M.: Deep neural network baseline for DCASE challenge 2016. In: Proceedings of DCASE 2016 (2016)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Cotton, C.V., Ellis, D.P.: Spectral vs. spectro-temporal features for acoustic event detection. In: 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 69\u201372. IEEE (2011)","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, H., McLoughlin, I., Song, Y.: Robust sound event recognition using convolutional neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 559\u2013563. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zou, Y., Shi, W.: Dilated convolution neural network with LeakyReLU for environmental sound classification. In: 2017 22nd International Conference on Digital Signal Processing (DSP), pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/ICDSP.2017.8096153"},{"key":"13_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/978-3-319-68612-7_40","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2017","author":"F Medhat","year":"2017","unstructured":"Medhat, F., Chesmore, D., Robinson, J.: Masked conditional neural networks for audio classification. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10614, pp. 349\u2013358. Springer, Cham (2017). \nhttps:\/\/doi.org\/10.1007\/978-3-319-68612-7_40"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Tokozume, Y., Harada, T.: Learning environmental sounds with end-to-end convolutional neural network. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2721\u20132725. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"13_CR16","unstructured":"Tokozume, Y., Ushiku, Y., Harada, T.: Learning from between-class examples for deep sound recognition. arXiv preprint \narXiv:1711.10282\n\n (2017)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Dai, W., Dai, C., Qu, S., Li, J., Das, S.: Very deep convolutional neural networks for raw waveforms. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 421\u2013425. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Hoshen, Y., Weiss, R.J., Wilson, K.W.: Speech acoustic modeling from raw multichannel waveforms. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4624\u20134628. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"13_CR19","doi-asserted-by":"crossref","first-page":"162","DOI":"10.21629\/JSEE.2017.01.18","volume":"28","author":"B Zhao","year":"2017","unstructured":"Zhao, B., Lu, H., Chen, S., Liu, J., Wu, D.: Convolutional neural networks for time series classification. J. Syst. Eng. Electron. 28, 162\u2013169 (2017)","journal-title":"J. Syst. Eng. Electron."},{"key":"13_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint \narXiv:1502.03167\n\n (2015)"},{"key":"13_CR21","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1109\/LSP.2017.2713830","volume":"24","author":"J Lee","year":"2017","unstructured":"Lee, J., Nam, J.: Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging. IEEE Signal Process. Lett. 24, 1208\u20131212 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 1041\u20131044. ACM (2014)","DOI":"10.1145\/2647868.2655045"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: ESC: dataset for environmental sound classification. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1015\u20131018. ACM (2015)","DOI":"10.1145\/2733373.2806390"},{"key":"13_CR24","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML, p. 3 (2013)"},{"key":"13_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint \narXiv:1412.6980\n\n (2014)"},{"key":"13_CR26","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24, 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05716-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:25:22Z","timestamp":1544451922000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"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":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - 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"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown 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"}}]}}