{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:15:29Z","timestamp":1762341329166},"reference-count":14,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2019,10,1]]},"DOI":"10.1587\/transinf.2019edl8062","type":"journal-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T22:47:08Z","timestamp":1569883628000},"page":"2055-2058","source":"Crossref","is-referenced-by-count":3,"title":["Multi Model-Based Distillation for Sound Event Detection"],"prefix":"10.1587","volume":"E102.D","author":[{"given":"Yingwei","family":"FU","sequence":"first","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Processing"},{"name":"College of Computer, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kele","family":"XU","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Processing"},{"name":"College of Computer, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibo","family":"MI","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Processing"},{"name":"College of Computer, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"KONG","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezhi","family":"WANG","sequence":"additional","affiliation":[{"name":"College of Meteorology and Oceanography, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaimin","family":"WANG","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Processing"},{"name":"College of Computer, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie","family":"HONG","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] A. Mesaros, T. Heittola, A. Eronen, and T. Virtanen, \u201cAcoustic event detection in real life recordings,\u201d IEEE 2010 18th European Signal Processing Conference, pp.1267-1271, 2010."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] T. Heittola, A. Mesaros, T. Virtanen, and M. Gabbouj, \u201cSupervised model training for overlapping sound events based on unsupervised source separation,\u201d ICASSP, pp.8677-8681, IEEE, 2013. 10.1109\/icassp.2013.6639360","DOI":"10.1109\/ICASSP.2013.6639360"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M. Espi, M. Fujimoto, K. Kinoshita, and T. Nakatani, \u201cExploiting spectro-temporal locality in deep learning based acoustic event detection,\u201d EURASIP Journal on Audio, Speech, and Music Processing, vol.2015, no.1, p.26, 2015. 10.1186\/s13636-015-0069-2","DOI":"10.1186\/s13636-015-0069-2"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] G. Parascandolo, H. Huttunen, and T. Virtanen, \u201cRecurrent neural networks for polyphonic sound event detection in real life recordings,\u201d ICASSP, pp.6440-6444, IEEE, 2016. 10.1109\/icassp.2016.7472917","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"5","unstructured":"[5] D. Wang, L. Zhang, C. Bao, K. Xu, B. Zhu, and Q. Kong, \u201cWeakly supervised CRNN system for sound event detection with large-scale unlabeled in-domain data,\u201d CoRR, abs\/1811.00301, 2018."},{"key":"6","unstructured":"[6] G. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network,\u201d CoRR, abs\/1503.02531, 2015."},{"key":"7","unstructured":"[7] K. Koutini, H. Eghbal-zadeh, and G. Widmer, \u201cIterative knowledge distillation in R-CNNs for weakly-labeled semi-supervised sound event detection,\u201d tech. rep., DCASE2018 Challenge, 2018."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Y. Xu, Q. Kong, W. Wang, and M.D. Plumbley, \u201cLarge-scale weakly supervised audio classification using gated convolutional neural network,\u201d ICASSP, pp.121-125, IEEE, 2018. 10.1109\/icassp.2018.8461975","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d CVPR, pp.770-778, IEEE, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] F. Chollet, \u201cXception: Deep Learning with Depthwise Separable Convolutions,\u201d CVPR, pp.1800-1807, IEEE, 2017. 10.1109\/cvpr.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] G. Huang, Z. Liu, L.V.D. Maaten, and K.Q. Weinberger, \u201cDensely connected convolutional networks,\u201d CVPR, pp.4700-4708, 2017. 10.1109\/cvpr.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, \u201cRethinking the inception architecture for computer vision,\u201d CVPR, pp.2818-2826, 2016. 10.1109\/cvpr.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, \u201cLearning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation,\u201d EMNLP, pp.1724-1734, Association for Computational Linguistics, 2014. 10.3115\/v1\/d14-1179","DOI":"10.3115\/v1\/D14-1179"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] A. Mesaros, T. Heittola, and T. Virtanen, \u201cMetrics for polyphonic sound event detection,\u201d Applied Sciences, vol.6, no.6, p.162, 2016. 10.3390\/app6060162","DOI":"10.3390\/app6060162"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/10\/E102.D_2019EDL8062\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T23:26:21Z","timestamp":1570231581000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/10\/E102.D_2019EDL8062\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,1]]},"references-count":14,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019edl8062","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,1]]}}}