{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:49:29Z","timestamp":1768819769540,"version":"3.49.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC Grant No.61550110248"],"award-info":[{"award-number":["NSFC Grant No.61550110248"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s11042-020-10330-9","type":"journal-article","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T04:36:35Z","timestamp":1609907795000},"page":"11459-11469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A sample-level DCNN for music auto-tagging"],"prefix":"10.1007","volume":"80","author":[{"given":"Yong-bin","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-hui","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-fan","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan-xin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Mai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nima","family":"Zhaxi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,6]]},"reference":[{"key":"10330_CR1","unstructured":"Bertin-Mahieux T, Ellis DP, Whitman B, Lamere P (2011) The million song dataset in Proceedings of the 12th International Society for Music Information Retrieval Conference. ISMIR 2011, Miami"},{"key":"10330_CR2","doi-asserted-by":"crossref","unstructured":"Choi K, Fazekas G, Sandler M, Cho K, Ieee (2017) Convolutional recurrent neural networks for music classification. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, pp 2392\u20132396","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"10330_CR3","doi-asserted-by":"crossref","unstructured":"Dieleman S, Schrauwen B, Ieee (2014) End-to-end learning for music audio. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, pp 6964\u20136968","DOI":"10.1109\/ICASSP.2014.6854950"},{"issue":"2","key":"10330_CR4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1109\/TMM.2010.2098858","volume":"13","author":"Z Fu","year":"2011","unstructured":"Fu Z, Lu G, Ting KM, Zhang D (2011) A survey of audio-based music classification and annotation. IEEE Trans Multimed 13(2):303\u2013319","journal-title":"IEEE Trans Multimed"},{"key":"10330_CR5","unstructured":"He K, Zhang X, Ren S, Sun J, Ieee (2016) Deep residual learning for image recognition in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, pp 770\u2013778"},{"key":"10330_CR6","doi-asserted-by":"crossref","unstructured":"Holschneider M, Kronland-Martinet R, Morlet J, Tchamitchian P, Combes JM, Grossman A (1989) A real-time algorithm for signal analysis with the help of the wavelet transform. Wavelets, Time-Frequency Methods and Phase Space 1:286","DOI":"10.1007\/978-3-642-97177-8_28"},{"key":"10330_CR7","doi-asserted-by":"crossref","unstructured":"Hoshen Y, Weiss RJ, Wilson KW (2015) Speech acoustic modeling from raw multichannel waveforms. In 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), International Conference on Acoustics Speech and Signal Processing ICASSP, Brisbane, pp 4624\u20134628","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"10330_CR8","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 42:2011\u20132023","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"10330_CR9","doi-asserted-by":"crossref","unstructured":"Kim T, Lee J, Nam J (2019) Comparison and analysis of sample cnn architectures for audio classification. IEEE Journal of Selected Topics in Signal Processing 13:285\u2013297","DOI":"10.1109\/JSTSP.2019.2909479"},{"key":"10330_CR10","doi-asserted-by":"crossref","unstructured":"Kumar A, Rajpal A, Rathore D (2018) Genre classification using feature extraction and deep learning techniques in 2018 10th International Conference on Knowledge and Systems Engineering (KSE), Ho Chi Minh City, pp 175\u2013180","DOI":"10.1109\/KSE.2018.8573325"},{"key":"10330_CR11","doi-asserted-by":"crossref","unstructured":"Lee J, Nam J (2017) Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging. Ieee Signal Processing Letters 24(8):1208\u20131212","DOI":"10.1109\/LSP.2017.2713830"},{"key":"10330_CR12","unstructured":"Lee J, Park J, Kim KL, Nam J (2017) Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms. ArXiv vol. abs\/1703.01789"},{"key":"10330_CR13","unstructured":"Lin Y, Chung C, Chen HH (2018) Playlist-based tag propagation for improving music auto-tagging in European Signal Processing Conference (EUSIPCO). European Signal Processing Conference, Rome, pp 2270\u20132274"},{"key":"10330_CR14","doi-asserted-by":"crossref","unstructured":"Nam J, Choi K, Lee J, Chou S, Yang Y (2019) Deep learning for audio-based music classification and tagging teaching computers to distinguish rock from bach. IEEE Signal Processing Magazine 36(1):41\u201351","DOI":"10.1109\/MSP.2018.2874383"},{"key":"10330_CR15","unstructured":"Oord AVD, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499"},{"key":"10330_CR16","doi-asserted-by":"crossref","unstructured":"Pons J, Lidy T, Serra X, Ieee (2016) Experimenting with musically motivated convolutional neural networks. In 2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI), Bucharest, pp 1\u20136","DOI":"10.1109\/CBMI.2016.7500246"},{"key":"10330_CR17","doi-asserted-by":"crossref","unstructured":"Rajanna AR, Aryafar K, Shokoufandeh A, Ptucha R (2015) Deep neural networks: A case study for music genre classification. 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, pp 655\u2013660","DOI":"10.1109\/ICMLA.2015.160"},{"key":"10330_CR18","doi-asserted-by":"crossref","unstructured":"Song G, Wang Z, Han F, Ding S, Iqbal MA (2018) Music auto-tagging using deep Recurrent Neural . Neurocomputing 292:104\u2013110","DOI":"10.1016\/j.neucom.2018.02.076"},{"key":"10330_CR19","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: A simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u20131958"},{"key":"10330_CR20","unstructured":"Ulaganathan AS, Ramanna S (2019) Granular methods in automatic music genre classification: a case study. J Intell Inf Syst 52(1)85\u2013105"},{"key":"10330_CR21","unstructured":"van den Oord A, Kalchbrenner N, Vinyals O, Espeholt L, Graves A, Kavukcuoglu K (2016) Conditional image generation with pixelcnn decoders. Advances in Neural Information Processing Systems 29 (Nips 2016) 29"},{"key":"10330_CR22","doi-asserted-by":"crossref","unstructured":"Zen H, Agiomyrgiannakis Y, Egberts N, Henderson F, Szczepaniak P (2016) Fast, compact, and high quality lstm-rnn based statistical parametric speech synthesizers for mobile devices. 17th Annual Conference of the International Speech Communication Association (Interspeech 2016), vols 1\u20135: Understanding Speech Processing in Humans and Machines, pp 2273\u20132277","DOI":"10.21437\/Interspeech.2016-522"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10330-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-10330-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10330-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T05:46:39Z","timestamp":1618551999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-10330-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,6]]},"references-count":22,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["10330"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-10330-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,6]]},"assertion":[{"value":"24 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}