{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:10:15Z","timestamp":1781007015224,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T00:00:00Z","timestamp":1434931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Municipal Natural Science Foundation","award":["13ZR1403800"],"award-info":[{"award-number":["13ZR1403800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,22]]},"DOI":"10.1145\/2671188.2749367","type":"proceedings-article","created":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T15:37:08Z","timestamp":1434987428000},"page":"379-386","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["A Deep Neural Network for Modeling Music"],"prefix":"10.1145","author":[{"given":"Pengjing","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqing","family":"Zheng","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyan","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Qian","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"He","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangtong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"e_1_3_2_1_2_1","volume-title":"Large Scale Kernel Machines, L. Bottou, O. Chapelle, D. DeCoste, and J. Weston (eds)","author":"Bengio Y.","year":"2007","unstructured":"Y. Bengio and Y. LeCun . Scaling learning algorithms towards AI . In Large Scale Kernel Machines, L. Bottou, O. Chapelle, D. DeCoste, and J. Weston (eds) . MIT Press , 2007 . Y. Bengio and Y. LeCun. Scaling learning algorithms towards AI. In Large Scale Kernel Machines, L. Bottou, O. Chapelle, D. DeCoste, and J. Weston (eds). MIT Press, 2007."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-61520-919-4.ch014"},{"key":"e_1_3_2_1_4_1","volume-title":"The million song dataset","author":"Bertin-Mahieux T.","year":"2011","unstructured":"T. Bertin-Mahieux , D. P. W. Ellis , B. Whitman , and P. Lamere . The million song dataset . In International Society for Music Information Retrieval (ISMIR '11), 2011 . T. Bertin-Mahieux, D. P. W. Ellis, B. Whitman, and P. Lamere. The million song dataset. In International Society for Music Information Retrieval (ISMIR'11), 2011."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916370"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning (ICML'11)","author":"Coates A.","year":"2011","unstructured":"A. Coates and A. Y. Ng . The importance of encoding versus training with sparse coding and vector quantization . In International Conference on Machine Learning (ICML'11) , 2011 . A. Coates and A. Y. Ng. The importance of encoding versus training with sparse coding and vector quantization. In International Conference on Machine Learning (ICML'11), 2011."},{"key":"e_1_3_2_1_7_1","volume-title":"Audio-based music classification with a pretrained convolutional network","author":"Dielemann S.","year":"2011","unstructured":"S. Dielemann , P. Brakel , and B. Schrauwen . Audio-based music classification with a pretrained convolutional network . In International Society for Music Information Retrieval (ISMIR '11), 2011 . S. Dielemann, P. Brakel, and B. Schrauwen. Audio-based music classification with a pretrained convolutional network. In International Society for Music Information Retrieval (ISMIR'11), 2011."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2098858"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1037\/1528-3542.7.2.377"},{"key":"e_1_3_2_1_10_1","volume-title":"Learning features from music audio with deep belief networks","author":"Hamel P.","year":"2010","unstructured":"P. Hamel and D. Eck . Learning features from music audio with deep belief networks . In International Society for Music Infromation Retrieval (ISMIR '10), 2010 . P. Hamel and D. Eck. Learning features from music audio with deep belief networks. In International Society for Music Infromation Retrieval (ISMIR'10), 2010."},{"key":"e_1_3_2_1_11_1","volume-title":"Temporal pooling and multiscale learning for automatic annotation and ranking of music audio","author":"Hamel P.","year":"2011","unstructured":"P. Hamel , S. Lemieux , Y. Bengio , and D. Eck . Temporal pooling and multiscale learning for automatic annotation and ranking of music audio . In International Society for Music Infromation Retrieval (ISMIR '11), 2011 . P. Hamel, S. Lemieux, Y. Bengio, and D. Eck. Temporal pooling and multiscale learning for automatic annotation and ranking of music audio. In International Society for Music Infromation Retrieval (ISMIR'11), 2011."},{"key":"e_1_3_2_1_12_1","volume-title":"Unsupervised learning of sparse features for scalable audio classification","author":"Henaff M.","year":"2011","unstructured":"M. Henaff , K. Jarrett , K. Kavukcuoglu , and Y. LeCuu . Unsupervised learning of sparse features for scalable audio classification . In International Society for Music Information Retrieval (ISMIR '11), 2011 . M. Henaff, K. Jarrett, K. Kavukcuoglu, and Y. LeCuu. Unsupervised learning of sparse features for scalable audio classification. In International Society for Music Information Retrieval (ISMIR'11), 2011."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_1_14_1","volume-title":"Moving beyond feature design: deep architectures and automatic feature learning in music informatics","author":"Humphrey E. J.","year":"2012","unstructured":"E. J. Humphrey , J. P. Bello , and Y. LeCun . Moving beyond feature design: deep architectures and automatic feature learning in music informatics . In International Society for Music Information Retrieval (ISMIR '12), 2012 . E. J. Humphrey, J. P. Bello, and Y. LeCun. Moving beyond feature design: deep architectures and automatic feature learning in music informatics. In International Society for Music Information Retrieval (ISMIR'12), 2012."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2012.04.002"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Digital Audio Effects (DAFx'11)","author":"Kereliuk P. D. C.","year":"2011","unstructured":"P. D. C. Kereliuk . Sparse atomic modeling of audio: A review . In International Conference on Digital Audio Effects (DAFx'11) , 2011 . P. D. C. Kereliuk. Sparse atomic modeling of audio: A review. In International Conference on Digital Audio Effects (DAFx'11), 2011."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/43745"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Digital Audio Effects (DAFx'07)","author":"Lartillot O.","year":"2007","unstructured":"O. Lartillot and P. Toiviainen . A matlab toolbox for musical feature extraction from audio . In International Conference on Digital Audio Effects (DAFx'07) , 2007 . O. Lartillot and P. Toiviainen. A matlab toolbox for musical feature extraction from audio. In International Conference on Digital Audio Effects (DAFx'07), 2007."},{"key":"e_1_3_2_1_19_1","volume-title":"Neural Information Processing Systems (NIPS'09)","author":"Lee H.","year":"2009","unstructured":"H. Lee , P. Pham , Y. Largman , and A. Y. Ng . Unsupervised feature learning for audio classification using convolutional deep belief networks . In Neural Information Processing Systems (NIPS'09) , 2009 . H. Lee, P. Pham, Y. Largman, and A. Y. Ng. Unsupervised feature learning for audio classification using convolutional deep belief networks. In Neural Information Processing Systems (NIPS'09), 2009."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2012913"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Multimedia and Expo (ICME'00)","author":"Li G.","year":"2000","unstructured":"G. Li and A. A. Khokhar . Content-based indexing and retrieval of audio data using wavelets . In International Conference on Multimedia and Expo (ICME'00) , 2000 . G. Li and A. A. Khokhar. Content-based indexing and retrieval of audio data using wavelets. In International Conference on Multimedia and Expo (ICME'00), 2000."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911304"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-002-0065-0"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"key":"e_1_3_2_1_25_1","volume-title":"Learning tags that vary within a song","author":"Mandel M. I.","year":"2010","unstructured":"M. I. Mandel , D. Eck , and Y. Bengio . Learning tags that vary within a song . In International Society for Music Information Retrieval (ISMIR '10), 2010 . M. I. Mandel, D. Eck, and Y. Bengio. Learning tags that vary within a song. In International Society for Music Information Retrieval (ISMIR'10), 2010."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2199109"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2112333"},{"key":"e_1_3_2_1_28_1","volume-title":"Learning sparse feature representations for music annotation and retrieval","author":"Nam J.","year":"2012","unstructured":"J. Nam , J. Herrera , M. Slaney , and J. Smith . Learning sparse feature representations for music annotation and retrieval . In International Society for Music Information Retrieval (ISMIR '12), 2012 . J. Nam, J. Herrera, M. Slaney, and J. Smith. Learning sparse feature representations for music annotation and retrieval. In International Society for Music Information Retrieval (ISMIR'12), 2012."},{"key":"e_1_3_2_1_29_1","volume-title":"International Symposium on Music Information Retrieval","author":"Nam U.","year":"2001","unstructured":"U. Nam and J. Berger . Addressing the same but different - different but similar problem in automatic music classification . In International Symposium on Music Information Retrieval , 2001 . U. Nam and J. Berger. Addressing the same but different - different but similar problem in automatic music classification. In International Symposium on Music Information Retrieval, 2001."},{"key":"e_1_3_2_1_30_1","volume-title":"A text retrieval approach to content-based audio retrieval","author":"Riley M.","year":"2008","unstructured":"M. Riley , E. Heinen , and J. Ghosh . A text retrieval approach to content-based audio retrieval . In International Society for Music Information Retrieval (ISMIR '08), 2008 . M. Riley, E. Heinen, and J. Ghosh. A text retrieval approach to content-based audio retrieval. In International Society for Music Information Retrieval (ISMIR'08), 2008."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2011.102"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Digital Audio Effects (DAFx'08)","author":"Seyerlehner K.","year":"2008","unstructured":"K. Seyerlehner , G. Widmer , and P. Knees . Frame level audio similarity: A codebook approach . In International Conference on Digital Audio Effects (DAFx'08) , 2008 . K. Seyerlehner, G. Widmer, and P. Knees. Frame level audio similarity: A codebook approach. In International Conference on Digital Audio Effects (DAFx'08), 2008."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2348283.2348346"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature04485"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2390848.2390851"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2311016"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-59904-663-1.ch002"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"e_1_3_2_1_39_1","volume-title":"Automatic musical genre classification of audio signals","author":"Tzanetakis G.","year":"2001","unstructured":"G. Tzanetakis , G. Essl , and P. Cook . Automatic musical genre classification of audio signals . In International Society for Music Information Retrieval (ISMIR '01), 2001 . G. Tzanetakis, G. Essl, and P. Cook. Automatic musical genre classification of audio signals. In International Society for Music Information Retrieval (ISMIR'01), 2001."},{"key":"e_1_3_2_1_40_1","first-page":"2579","article-title":"Visualizing high-dimensional data using t-sne","volume":"9","author":"van der Maaten L. J. P.","year":"2008","unstructured":"L. J. P. van der Maaten and G. E. Hinton . Visualizing high-dimensional data using t-sne . Journal of Machine Learning Research , 9 : 2579 -- 2605 , 2008 . L. J. P. van der Maaten and G. E. Hinton. Visualizing high-dimensional data using t-sne. Journal of Machine Learning Research, 9:2579--2605, 2008.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953039"},{"key":"e_1_3_2_1_42_1","volume-title":"Learning the similarity of audio music in bag-of-frames representation from tagged music data","author":"Wang J.-C.","year":"2011","unstructured":"J.-C. Wang , H.-S. Lee , H.-M. Wang , and S.-K. Jeng . Learning the similarity of audio music in bag-of-frames representation from tagged music data . In International Society for Music Information Retrieval (ISMIR '11), 2011 . J.-C. Wang, H.-S. Lee, H.-M. Wang, and S.-K. Jeng. Learning the similarity of audio music in bag-of-frames representation from tagged music data. In International Society for Music Information Retrieval (ISMIR'11), 2011."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2324796.2324859"}],"event":{"name":"ICMR '15: International Conference on Multimedia Retrieval","location":"Shanghai China","acronym":"ICMR '15","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 5th ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749367","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2671188.2749367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:12:35Z","timestamp":1750227155000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749367"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,22]]},"references-count":43,"alternative-id":["10.1145\/2671188.2749367","10.1145\/2671188"],"URL":"https:\/\/doi.org\/10.1145\/2671188.2749367","relation":{},"subject":[],"published":{"date-parts":[[2015,6,22]]},"assertion":[{"value":"2015-06-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}