{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:56:10Z","timestamp":1776887770983,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/waspaa.2017.8169987","type":"proceedings-article","created":{"date-parts":[[2017,12,13]],"date-time":"2017-12-13T14:38:44Z","timestamp":1513175924000},"page":"21-25","source":"Crossref","is-referenced-by-count":111,"title":["Multi-Scale multi-band densenets for audio source separation"],"prefix":"10.1109","author":[{"given":"Naoya","family":"Takahashi","sequence":"first","affiliation":[]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Multichannel music separation with deep neural networks","author":"nugraha","year":"2015","journal-title":"Proc EU-SIPCO"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178348"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952158"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738895"},{"key":"ref17","author":"takahashi","year":"2017","journal-title":"Aenet Learning deep audio features for video analysis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"NIPS"},{"key":"ref28","first-page":"66","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref4","first-page":"6670","article-title":"Deep NMF for speech separation","author":"leroux","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref27","article-title":"rmsprop adaptive learning","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2332434"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471632"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2570945"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref20","author":"huang","year":"2016","journal-title":"Densely Connected Convolutional Networks"},{"key":"ref22","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref21","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Report"},{"key":"ref24","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref23","first-page":"66","article-title":"The 2016 Signal Separation Evaluation Campaign","author":"liutkus","year":"2017","journal-title":"Proceedings of the LVAlICA"},{"key":"ref26","article-title":"Exploring Convolutional Neural Network Structures and Optimization Techniques for Speech Recognition","author":"abdel-hamid","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref25","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc AISTATS"}],"event":{"name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY","start":{"date-parts":[[2017,10,15]]},"end":{"date-parts":[[2017,10,18]]}},"container-title":["2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8125199\/8169982\/08169987.pdf?arnumber=8169987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,17]],"date-time":"2018-01-17T18:13:18Z","timestamp":1516212798000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8169987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/waspaa.2017.8169987","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}