{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:40:33Z","timestamp":1779385233118,"version":"3.53.1"},"reference-count":43,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952158","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"261-265","source":"Crossref","is-referenced-by-count":133,"title":["Improving music source separation based on deep neural networks through data augmentation and network blending"],"prefix":"10.1109","author":[{"given":"Stefan","family":"Uhlich","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcello","family":"Porcu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franck","family":"Giron","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Enenkl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kemp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoya","family":"Takahashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"2016","journal-title":"Theano A Python framework for fast computation of mathematical expressions"},{"key":"ref38","year":"0","journal-title":"Theano GitHub"},{"key":"ref33","first-page":"315","article-title":"Deep sparse rectifier networks","volume":"15","author":"glorot","year":"2011","journal-title":"Pmc AISTATS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404834"},{"key":"ref31","volume":"1","author":"kay","year":"1993","journal-title":"Fundamentals of Statistical Signal Processing"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172425"},{"key":"ref37","year":"0","journal-title":"Lasagne GitHub"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref35","author":"duda","year":"2001","journal-title":"Pattern Classification and Scene Analysis"},{"key":"ref34","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178348"},{"key":"ref40","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"schl\u00fcter","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854299"},{"key":"ref13","first-page":"477","article-title":"Singing-voice separation from monaural recordings using deep recurrent neural networks","author":"huang","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_50"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701888"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2013.6661930"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2553441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-216"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2011.6004991"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177933"},{"key":"ref3","article-title":"Stereo music source separation for 3-D upmixing","author":"shim","year":"2009","journal-title":"127th AES Convention"},{"key":"ref6","year":"0","journal-title":"SiSEC MUS Homepage"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref5","article-title":"The good vibrations problem","author":"fitzgerald","year":"2013","journal-title":"134th AES Convention e-brief"},{"key":"ref8","article-title":"Multichannel audio source separation with deep neural networks","author":"nugraha","year":"2015","journal-title":"INRIA technical report"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_45"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158801"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760548"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2213249"},{"key":"ref20","article-title":"Single-channel audio source separation using deep neural network ensembles","author":"grais","year":"2016","journal-title":"140th AES Convention"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"ref21","first-page":"1745","article-title":"Multi-resolution stacking for speech separation based on boosted DNN","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref42","first-page":"35","article-title":"The Netflix prize","volume":"2007","author":"bennett","year":"2007","journal-title":"Proc KDD Cup and Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1381036"},{"key":"ref41","article-title":"A software framework for musical data augmentation","author":"mcfee","year":"0","journal-title":"Proc ISMIR 2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178939"},{"key":"ref26","first-page":"865","article-title":"Discriminative NMF and its application to single-channel source separation","author":"weninger","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1345448.1345465"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA","start":{"date-parts":[[2017,3,5]]},"end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07952158.pdf?arnumber=7952158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,3]],"date-time":"2017-10-03T01:41:04Z","timestamp":1506994864000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7952158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952158","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}