{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T01:14:18Z","timestamp":1790385258682,"version":"4.1.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462046","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"366-370","source":"Crossref","is-referenced-by-count":61,"title":["Sample-Level CNN Architectures for Music Auto-Tagging Using Raw Waveforms"],"prefix":"10.1109","author":[{"given":"Taejun","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jongpil","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref12","author":"hu","year":"2017","journal-title":"Squeeze-and-Excitation Networks"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref14","article-title":"Multi-level and multiscale feature aggregation using sample-level deep convolutional neural networks for music classification","author":"lee","year":"2017","journal-title":"Machine learning for music discovery workshop international conference on machine learning (icml)"},{"key":"ref15","first-page":"1891","article-title":"Deep learning face representation from predicting 10,000 classes","author":"sun","year":"2014","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref16","first-page":"647","article-title":"De-caf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref17","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref18","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"British Machine Vision Conference (BMVC)"},{"key":"ref19","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"International Society of Music Information Retrieval Conference (IS-MIR)"},{"key":"ref4","article-title":"Transfer learning by supervised pretraining for audio-based music classification","author":"van den oord","year":"2014","journal-title":"International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref3","first-page":"116","article-title":"Multi-scale approaches to music audio feature learning","author":"dieleman","year":"2013","journal-title":"International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref5","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"2016","journal-title":"International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref8","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","author":"lee","year":"2017","journal-title":"Sound and Music Computing (SMC) Conference"},{"key":"ref7","first-page":"421","article-title":"Very deep convolutional neural networks for raw waveforms","author":"dai","year":"2017","journal-title":"ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2713830"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref20","first-page":"10","article-title":"The million song dataset","volume":"2","author":"bertin-mahieux","year":"2011","journal-title":"International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref22","first-page":"2101","article-title":"Brains on beats","author":"g\u00fc\u00e7l\u00fc","year":"2016","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref21","author":"liu","year":"2016","journal-title":"Applying topological persistence in convolutional neural network for music audio signals"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081710"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462046.pdf?arnumber=8462046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:29:02Z","timestamp":1598243342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462046","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}