{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T17:44:44Z","timestamp":1762623884419},"reference-count":21,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2017]]},"DOI":"10.1587\/transinf.2017edl8048","type":"journal-article","created":{"date-parts":[[2017,8,31]],"date-time":"2017-08-31T18:27:26Z","timestamp":1504204046000},"page":"2249-2252","source":"Crossref","is-referenced-by-count":12,"title":["DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification"],"prefix":"10.1587","volume":"E100.D","author":[{"given":"Seongkyu","family":"MUN","sequence":"first","affiliation":[{"name":"Department of Visual Information Processing, Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minkyu","family":"SHIN","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suwon","family":"SHON","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wooil","family":"KIM","sequence":"additional","affiliation":[{"name":"Dept. of Computer Science and Engineering, Incheon National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David K.","family":"HAN","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanseok","family":"KO","sequence":"additional","affiliation":[{"name":"Department of Visual Information Processing, Korea University"},{"name":"School of Electrical Engineering, Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] S. Mun, S. Shon, W. Kim, and H. Ko, \u201cDeep neural network bottleneck features for acoustic event recognition,\u201d Proc. of the Int. Speech Comm. Association, INTERSPEECH 2016, San Francisco, USA, pp.2954-2957, Sept. 2016. 10.21437\/interspeech.2016-1112","DOI":"10.21437\/Interspeech.2016-1112"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] J. Lude\u00f1a-Choez and A. Gallardo-Antol\u00edn, \u201cFeature extraction based on the high-pass filtering of audio signals for Acoustic Event Classification,\u201d Computer Speech & Language, vol.30, no.1, pp.32-42, 2015. 10.1016\/j.csl.2014.04.001","DOI":"10.1016\/j.csl.2014.04.001"},{"key":"3","unstructured":"[3] W. Choi, S. Park, D.K. Han, and H. Ko, \u201cAcoustic event recognition using dominant spectral basis vectors,\u201d Proc. of the Int. Speech Comm. Association, INTERSPEECH 2015, Dresden, Germany, pp.2002-2006, Sept. 2015."},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] S. Park, W. Choi, D.K. Han, and H. Ko, \u201cAcoustic event filterbank for enabling robust event recognition by cleaning robot, IEEE Trans. Consum. Electron., vol.61, no.2, pp.189-196, 2015. 10.1109\/tce.2015.7150593","DOI":"10.1109\/TCE.2015.7150593"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] A. Kumar and B. Raj, \u201cAudio event detection using weakly labeled data,\u201d ACM 2016 Int. Conf. on Multimedia, Amsterdam, Netherlands, pp.1038-1047, Oct. 2016. 10.1145\/2964284.2964310","DOI":"10.1145\/2964284.2964310"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] X.-L. Zhang and J. Wu, \u201cDeep belief networks based voice activity detection,\u201d IEEE Trans. Speech Audio Process., vol.21, no.4, pp.697-710, 2013. 10.1109\/tasl.2012.2229986","DOI":"10.1109\/TASL.2012.2229986"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Y. Xu, J. Du, L.-R. Dai, and C.-H. Lee, \u201cAn experimental study on speech enhancement based on deep neural networks,\u201d IEEE Signal Proc. Letters, vol.21, no.1, pp.65-68, 2014. 10.1109\/lsp.2013.2291240","DOI":"10.1109\/LSP.2013.2291240"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] M. Oquab, L. Bottou, I. Laptev, and J. Sivic, \u201cLearning and transferring mid-level image representations using convolutional neural networks,\u201d IEEE Conf. on Computer Vision and Pattern Recog. (CVPR), Columbus, USA, pp.1717-1724, June 2014. 10.1109\/cvpr.2014.222","DOI":"10.1109\/CVPR.2014.222"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] J. Gehring, Y. Miao, F. Metze, and A. Waibel, \u201cExtracting deep bottleneck features using stacked auto-encoders,\u201d IEEE Int. Conf. on Acoustics, Speech and Signal Proc., Vancouver, Canada, pp.3377-3381, May 2013. 10.1109\/icassp.2013.6638284","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] A. Temko, R. Malkin, C. Zieger, D. Macho, C. Nadeu, and M. Omologo, \u201cCLEAR evaluation of acoustic event detection and classification systems,\u201d Proc. of Int. Eval. Work. on Classification of Events, Act. and Relation., pp.311-322, 2007. 10.1007\/978-3-540-69568-4_29","DOI":"10.1007\/978-3-540-69568-4_29"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] S. Nakamura, K. Hiyane, F. Asano, T. Yamada, T. Endo, \u201cData collection in real acoustical environments for sound scene understanding and hands-free speech recognition', in Proc. of EUROSPEECH, pp.2255-2258, 1999. 10.1250\/ast.20.225","DOI":"10.1250\/ast.20.225"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] J. Salamon, C. Jacoby, and J.P. Bello, \u201cA dataset and taxonomy for urban sound research,\u201d ACM 2014 Int. Conf. on Multimedia, New York, USA, pp.1041-1044, Oct. 2014. 10.1145\/2647868.2655045","DOI":"10.1145\/2647868.2655045"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] K.J. Piczak, \u201cESC: Dataset for environmental sound classification,\u201d ACM 2015 Int. Conf. on Multimedia, Brisbane, Australia, pp.1015-1018, Oct. 2015. 10.1145\/2733373.2806390","DOI":"10.1145\/2733373.2806390"},{"key":"14","unstructured":"[14] http:\/\/www.prosoundeffects.com\/pdf\/BBC-Complete.pdf"},{"key":"15","unstructured":"[15] http:\/\/www.sound-ideas.com"},{"key":"16","unstructured":"[16] http:\/\/www.sonycreativesoftware.com\/sfxseries"},{"key":"17","unstructured":"[17] European Telecommunications Standards Institute, \u201cETSI: EG 202 396-1 v1.2.2,\u201d 2008."},{"key":"18","unstructured":"[18] P. Hamel and D. Eck, \u201cLearning features from music audio with deep belief networks,\u201d Int. Society for Music Infor. Retri. Conf., ISMIR 2010, Utrecht, Netherlands, pp.339-344, Aug. 2010."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] T.N. Sainath, R.J. Weiss, K.W. Wilson, B. Li, A. Narayanan, E. Variani, M. Bacchiani, I. Shafran, A. Senior, K. Chin, A. Misra, and C. Kim, \u201cMultichannel signal processing with deep neural network for automatic speech recognition,\u201d IEEE\/ACM trans. on Audio Speech Lang. Proc., vol.25, no.5, pp.965-979, 2017. 10.1109\/taslp.2017.2672401","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] W. Dai, C. Dai, S. Qu, J. Li, and S. Das, \u201cVery deep convolutional neural networks for raw waveform,\u201d IEEE Int. Conf. on Acoustics, Speech and Signal Proc., Neworleans, USA, pp.421-425, May 2017. 10.1109\/icassp.2017.7952190","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] M. Espi, M. Fujimoto, and T. Nakatani, \u201cAcoustic event detection in speech overlapping scenarios based on high-resolution spectral input and deep learning,\u201d IEICE trans. Inf. & Syst., vol.E98-D, no.10, pp.1799-1807, 2015. 10.1587\/transinf.2014edp7430","DOI":"10.1587\/transinf.2014EDP7430"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/9\/E100.D_2017EDL8048\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,2]],"date-time":"2019-10-02T20:59:38Z","timestamp":1570049978000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/9\/E100.D_2017EDL8048\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":21,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2017edl8048","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}