{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:32:15Z","timestamp":1782401535938,"version":"3.54.5"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T00:00:00Z","timestamp":1603756800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T00:00:00Z","timestamp":1603756800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61672130"],"award-info":[{"award-number":["No.61672130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61602082"],"award-info":[{"award-number":["No.61602082"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.91648205"],"award-info":[{"award-number":["No.91648205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012149","name":"National Key Scientific Instrument and Equipment Development Projects of China","doi-asserted-by":"publisher","award":["No. 61627808"],"award-info":[{"award-number":["No. 61627808"]}],"id":[{"id":"10.13039\/501100012149","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":[[2021,2]]},"DOI":"10.1007\/s11042-020-09643-6","type":"journal-article","created":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T20:13:55Z","timestamp":1603829635000},"page":"7313-7331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":83,"title":["Bottom-up broadcast neural network for music genre classification"],"prefix":"10.1007","volume":"80","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4942-2293","authenticated-orcid":false,"given":"Caifeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guochao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huibing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenglan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,27]]},"reference":[{"key":"9643_CR1","unstructured":"Bertin-Mahieux T, Ellis DP, Whitman B, Lamere P (2011) The million song dataset. In: Ismir, vol 2, pp 10"},{"key":"9643_CR2","unstructured":"Cano P, G\u00f3mez Guti\u00e9rrez E, Gouyon F, Herrera Boyer P, Koppenberger M, Ong BS, Serra X, Streich S, Wack N (2006) Ismir 2004 audio description contest"},{"key":"9643_CR3","unstructured":"Choi K, Fazekas G, Sandler M, Cho K (2017) Transfer learning for music classification and regression tasks. arXiv:1703.09179"},{"key":"9643_CR4","unstructured":"Chollet F et al (2015) Keras"},{"key":"9643_CR5","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.asoc.2016.12.024","volume":"52","author":"YM Costa","year":"2017","unstructured":"Costa YM, Oliveira LS, Silla CN Jr (2017) An evaluation of convolutional neural networks for music classification using spectrograms. Applied Soft Computing 52:28\u201338","journal-title":"Applied Soft Computing"},{"key":"9643_CR6","doi-asserted-by":"crossref","unstructured":"Dai J, Liu W, Ni C, Dong L, Yang H (2015) \u201cmultilingual\u201d deep neural network for music genre classification. In: Sixteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2015-448"},{"issue":"1","key":"9643_CR7","first-page":"6340","volume":"18","author":"M Freitag","year":"2017","unstructured":"Freitag M, Amiriparian S, Pugachevskiy S, Cummins N (2017) Schuller, B.: audeep: Unsupervised learning of representations from audio with deep recurrent neural networks. J Mach Learn Res 18(1):6340\u20136344","journal-title":"J Mach Learn Res"},{"issue":"2","key":"9643_CR8","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 Multimedia 13(2):303\u2013319","journal-title":"IEEE Trans Multimedia"},{"key":"9643_CR9","doi-asserted-by":"crossref","unstructured":"Hafemann LG, Oliveira LS, Cavalin P (2014) Forest species recognition using deep convolutional neural networks. In: 2014 22nd international conference on Pattern recognition (ICPR), IEEE, pp 1103\u20131107","DOI":"10.1109\/ICPR.2014.199"},{"issue":"1","key":"9643_CR10","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The weka data mining software: an update. ACM SIGKDD Explorations Newsletter 11(1):10\u201318","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"9643_CR11","unstructured":"Hamel P, Eck D (2010) Learning features from music audio with deep belief networks. In: ISMIR, vol 10, Utrecht, pp 339\u2013344"},{"key":"9643_CR12","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"9643_CR13","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, vol 1, pp 3","DOI":"10.1109\/CVPR.2017.243"},{"key":"9643_CR14","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization:, Accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167"},{"key":"9643_CR15","doi-asserted-by":"crossref","unstructured":"Jakubik J (2017) Evaluation of gated recurrent neural networks in music classification tasks. In: International conference on information systems architecture and technology, Springer, pp 27\u201337","DOI":"10.1007\/978-3-319-67220-5_3"},{"key":"9643_CR16","unstructured":"Jeong Y, Choi K, Jeong H (2017) Dlr:, Toward a deep learned rhythmic representation for music content analysis. arXiv:1712.05119"},{"key":"9643_CR17","doi-asserted-by":"crossref","unstructured":"Karunakaran N, Arya A (2018) A scalable hybrid classifier for music genre classification using machine learning concepts and spark. In: 2018 International conference on intelligent autonomous systems (ICoIAS), IEEE, pp 128\u2013135","DOI":"10.1109\/ICoIAS.2018.8494161"},{"issue":"11","key":"9643_CR18","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1109\/TMM.2015.2478068","volume":"17","author":"C Kereliuk","year":"2015","unstructured":"Kereliuk C, Sturm BL, Larsen J (2015) Deep learning and music adversaries. IEEE Trans Multimedia 17(11):2059\u20132071","journal-title":"IEEE Trans Multimedia"},{"key":"9643_CR19","unstructured":"Kingma DP, Ba J (2014) Adam:, A method for stochastic optimization. arXiv:1412.6980"},{"key":"9643_CR20","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"issue":"8","key":"9643_CR21","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1109\/LSP.2017.2713830","volume":"24","author":"J Lee","year":"2017","unstructured":"Lee J, Nam J (2017) Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging. IEEE Signal Process Lett 24(8):1208\u20131212","journal-title":"IEEE Signal Process Lett"},{"key":"9643_CR22","unstructured":"Lee H, Pham P, Largman Y, Ng AY (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in neural information processing systems, pp1096\u20131104"},{"key":"9643_CR23","unstructured":"Li TL, Chan AB, Chun A (2010) Automatic musical pattern feature extraction using convolutional neural network. In: Proc Int Conf Data mining and applications"},{"key":"9643_CR24","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv:1312.4400"},{"key":"9643_CR25","unstructured":"Lykartsis A, Lerch A (2015) Beat histogram features for rhythm-based musical genre classification using multiple novelty functions. In: Proceedings of the 16th ISMIR Conference, pp 434\u2013440"},{"key":"9643_CR26","unstructured":"Marchand U, Peeters G (2016) The extended ballroom dataset"},{"key":"9643_CR27","unstructured":"Marchand U, Peeters G (2014) The modulation scale spectrum and its application to rhythm-content analysis. In: DAFX (Digital audio effects)"},{"key":"9643_CR28","doi-asserted-by":"crossref","unstructured":"Marchand U, Peeters G (2016) Scale and shift invariant time\/frequency representation using auditory statistics: Application to rhythm description. In: 2016 IEEE 26th international workshop on Machine learning for signal processing (MLSP), IEEE, pp 1\u20136","DOI":"10.1109\/MLSP.2016.7738904"},{"key":"9643_CR29","doi-asserted-by":"crossref","unstructured":"McFee B, Raffel C, Liang D, Ellis DP, McVicar M, Battenberg E (2015) Nieto, O.: librosa: Audio and music signal analysis in python. In: Proceedings of the 14th python in science conference, pp 18\u201325","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"9643_CR30","doi-asserted-by":"crossref","unstructured":"Medhat F, Chesmore D, Robinson J (2017) Automatic classification of music genre using masked conditional neural networks. In: 2017 IEEE international conference on Data mining (ICDM), IEEE, pp 979\u2013984","DOI":"10.1109\/ICDM.2017.125"},{"key":"9643_CR31","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.patrec.2017.01.013","volume":"88","author":"L Nanni","year":"2017","unstructured":"Nanni L, Costa YM, Lucio DR, Silla CN Jr, Brahnam S (2017) Combining visual and acoustic features for audio classification tasks. Pattern Recogn Lett 88:49\u201356","journal-title":"Pattern Recogn Lett"},{"key":"9643_CR32","doi-asserted-by":"crossref","unstructured":"Nguyen QH, Do TT, Chu TB, Trinh LV, Nguyen DH, Phan CV, Phan TA, Doan DV, Pham HN, Nguyen BP et al (2019) Music genre classification using residual attention network. In: 2019 International conference on system science and engineering (ICSSE), IEEE, pp 115\u2013119","DOI":"10.1109\/ICSSE.2019.8823100"},{"key":"9643_CR33","doi-asserted-by":"crossref","unstructured":"Pons J, Serra X (2017) Designing efficient architectures for modeling temporal features with convolutional neural networks. In: 2017 IEEE international conference on Acoustics, speech and signal processing (ICASSP), IEEE, pp 2472\u20132476","DOI":"10.1109\/ICASSP.2017.7952601"},{"key":"9643_CR34","doi-asserted-by":"crossref","unstructured":"Pons J, Serra X (2018) Randomly weighted cnns for (music) audio classification. arXiv:1805.00237","DOI":"10.1109\/ICASSP.2019.8682912"},{"key":"9643_CR35","doi-asserted-by":"crossref","unstructured":"Pons J, Lidy T, Serra X (2016) Experimenting with musically motivated convolutional neural networks. In: 2016 14th international workshop on Content-based multimedia indexing (CBMI), IEEE, pp 1\u20136","DOI":"10.1109\/CBMI.2016.7500246"},{"issue":"3","key":"9643_CR36","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Processing Letters 24(3):279\u2013283","journal-title":"IEEE Signal Processing Letters"},{"key":"9643_CR37","doi-asserted-by":"crossref","unstructured":"Senac C, Pellegrini T, Mouret F, Pinquier J (2017) Music feature maps with convolutional neural networks for music genre classification. In: Proceedings of the 15th international workshop on content-based multimedia indexing, ACM, pp 19","DOI":"10.1145\/3095713.3095733"},{"key":"9643_CR38","doi-asserted-by":"crossref","unstructured":"Sigtia S, Dixon S (2014) Improved music feature learning with deep neural networks. In: 2014 IEEE international conference on Acoustics, speech and signal processing (ICASSP), IEEE, pp 6959\u20136963","DOI":"10.1109\/ICASSP.2014.6854949"},{"key":"9643_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"5","key":"9643_CR40","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis G, Cook P (2002) Musical genre classification of audio signals. IEEE Trans Speech Audio Process 10(5):293\u2013302","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"11","key":"9643_CR41","doi-asserted-by":"publisher","first-page":"3939","DOI":"10.1109\/TIP.2015.2457339","volume":"24","author":"Y Wang","year":"2015","unstructured":"Wang Y, Lin X, Wu L, Zhang W, Zhang Q, Huang X (2015) Robust subspace clustering for multi-view data by exploiting correlation consensus. IEEE Trans Image Process 24(11):3939\u20133949","journal-title":"IEEE Trans Image Process"},{"key":"9643_CR42","doi-asserted-by":"crossref","unstructured":"Wang Y, Lin X, Wu L, Zhang W (2017) Effective multi-query expansions:, Collaborative deep networks for robust landmark retrieval. arXiv:1701.05003","DOI":"10.1109\/TIP.2017.2655449"},{"issue":"1","key":"9643_CR43","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1109\/TNNLS.2015.2498149","volume":"28","author":"Y Wang","year":"2017","unstructured":"Wang Y, Zhang W, Wu L, Lin X, Zhao X (2017) Unsupervised metric fusion over multiview data by graph random walk-based cross-view diffusion. IEEE Trans Neural Netw Learn Syst 28(1):57\u201370","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"9643_CR44","doi-asserted-by":"crossref","unstructured":"Wang Y, Wu L, Lin X, Gao J (2018) Multiview spectral clustering via structured low-rank matrix factorization. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2017.2777489"},{"key":"9643_CR45","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2019.09.054","volume":"372","author":"Y Yu","year":"2020","unstructured":"Yu Y, Luo S, Liu S, Qiao H, Liu Y, Feng L (2020) Deep attention based music genre classification. Neurocomputing 372:84\u201391","journal-title":"Neurocomputing"},{"key":"9643_CR46","doi-asserted-by":"crossref","unstructured":"Zhang W, Lei W, Xu X, Xing X (2016) Improved music genre classification with convolutional neural networks. In: INTERSPEECH, pp 3304\u20133308","DOI":"10.21437\/Interspeech.2016-1236"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09643-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09643-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09643-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T23:39:02Z","timestamp":1635291542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09643-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,27]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["9643"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09643-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,27]]},"assertion":[{"value":"23 October 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}