{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:15:44Z","timestamp":1784333744587,"version":"3.55.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489641","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T18:25:09Z","timestamp":1539973509000},"page":"1-8","source":"Crossref","is-referenced-by-count":55,"title":["Learning Environmental Sounds with Multi-scale Convolutional Neural Network"],"prefix":"10.1109","author":[{"given":"Boqing","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref32","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","author":"lee","year":"2017","journal-title":"arXiv preprint arXiv 1703 01281"},{"key":"ref30","article-title":"Character-aware neural language models","author":"kim","year":"2015","journal-title":"Computer Science"},{"key":"ref10","first-page":"3668","article-title":"Feature learning with raw-waveform cldnns for voice activity detection","author":"zazo","year":"0"},{"key":"ref11","article-title":"Learning the speech front-end with raw waveform cldnns","author":"sainath","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref13","article-title":"Auditory scene classification using machine learning techniques","author":"david","year":"2013","journal-title":"AASP Challenge"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2375575"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","article-title":"Detection and classification of acoustic scenes and events","volume":"17","author":"dan","year":"2015","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref16","first-page":"1056","article-title":"Recurrence quantification analysis features for environmental sound recognition","volume":"51","author":"roma","year":"2013","journal-title":"Annals of the Rheumatic Diseases"},{"key":"ref17","first-page":"171","article-title":"Unsupervised feature learning for urban sound classification","author":"salamon","year":"0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.060"},{"key":"ref4","first-page":"1041","article-title":"A dataset and taxonomy for urban sound research","author":"salamon","year":"0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2673118"},{"key":"ref3","first-page":"421","article-title":"Very deep convolutional neural networks for raw waveforms","author":"dai","year":"0"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","article-title":"Classifying environmental sounds using image recognition networks","volume":"112","author":"boddapati","year":"0","journal-title":"Procedia Computer Science"},{"key":"ref29","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"2721","article-title":"Learning environmental sounds with endto-end convolutional neural network","author":"tokozume","year":"0"},{"key":"ref8","first-page":"18","article-title":"Classification and regression by randomforest","volume":"2","author":"liaw","year":"2002","journal-title":"R News"},{"key":"ref7","first-page":"1","article-title":"Dilated convolution neural network with leakyrelu for environmental sound classification","author":"zhang","year":"0"},{"key":"ref2","first-page":"1","article-title":"Environmental sound classification with convolutional neural networks","author":"piczak","year":"0"},{"key":"ref9","first-page":"4580","article-title":"Convolutional, long short-term memory, fully connected deep neural networks","author":"sainath","year":"0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref20","first-page":"135","article-title":"Sound classification in a smart room environment: an approach using gmm and hmm methods","volume":"1","author":"vacher","year":"0"},{"key":"ref22","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"0"},{"key":"ref21","first-page":"1809","article-title":"Novel teobased gammatone features for environmental sound classification","author":"agrawal","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref26","author":"ronneberger","year":"2015","journal-title":"U-net Convolutional networks for biomedical image segmentation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","location":"Rio de Janeiro","start":{"date-parts":[[2018,7,8]]},"end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489641.pdf?arnumber=8489641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:39:10Z","timestamp":1598211550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489641","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}