{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T14:25:20Z","timestamp":1789568720959,"version":"build-2803163510"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/iwaenc.2018.8521371","type":"proceedings-article","created":{"date-parts":[[2018,11,5]],"date-time":"2018-11-05T21:38:56Z","timestamp":1541453936000},"page":"421-425","source":"Crossref","is-referenced-by-count":12,"title":["Harmonic-Percussive Source Separation with Deep Neural Networks and Phase Recovery"],"prefix":"10.1109","author":[{"given":"Konstantinos","family":"Drossos","sequence":"first","affiliation":[{"name":"Tampere University of Technology, Laboratory of Signal Processing, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Magron","sequence":"additional","affiliation":[{"name":"Tampere University of Technology, Laboratory of Signal Processing, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stylianos Ioannis","family":"Mimilakis","sequence":"additional","affiliation":[{"name":"Tampere University of Technology, Laboratory of Signal Processing, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Tampere University of Technology, Laboratory of Signal Processing, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"mir.eval: A transparent implementation of common MIR metrics","author":"raffel","year":"2014","journal-title":"Proc International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref31","article-title":"Design criteria for simple sinusoidal parameter estimation based on quadratic interpolation of FFT magnitude peaks","author":"abe","year":"2004","journal-title":"Audio Eng Soc 117 Convention"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2354236"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461741"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2018-1845","article-title":"Re-ducing interference with phase recovery in DNN-based monaural singing voice separation","author":"magron","year":"2018","journal-title":"Proc of Interspeech"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-014-0026-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362741"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-30110-3_63","article-title":"Non-negative matrix factor deconvolution; extraction of multiple sound sources from monophonic inputs","author":"smaragdis","year":"2004","journal-title":"Proceedings of the International Conference on Independent Component Analysis and Blind Signal Separation"},{"key":"ref14","article-title":"Drum extraction in single channel audio signals using multilayer non negative matrix factor deconvolution","author":"laroche","year":"2017","journal-title":"Proc of IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580946"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"ref17","article-title":"A recurrent encoder-decoder approach with skip-filtering connections for monaural singing voice separation","author":"mimilakis","year":"2017","journal-title":"Proc IEEE International Workshop on Machine Learning for Signal Processing (MLSP)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461822"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489565"},{"key":"ref28","article-title":"Memory augmented neural networks with wormhole connections","volume":"abs 1701 8718","author":"g\u00fclcehre","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2294023"},{"key":"ref27","article-title":"Improving neural language models with a continuous cache","volume":"abs 1612 4426","author":"grave","year":"2016","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287906"},{"key":"ref6","article-title":"Harmonic\/percussive separation using kernel additive modelling","author":"fitzgerald","year":"2013","journal-title":"Proc IET Irish Signals Syst Conf"},{"key":"ref29","article-title":"Topicrnn: A recurrent neural network with long-range semantic dependency","volume":"abs 1611 1702","author":"dieng","year":"2016","journal-title":"CoRR"},{"key":"ref5","article-title":"Harmonic\/percussive separation using median filtering","author":"fitzgerald","year":"2010","journal-title":"Proc of International Conference on Digital Au-dio Fffects (DAFx)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2351131"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2332434"},{"key":"ref2","article-title":"Separation of a monaural audio signal into har-monic\/percussive components by complementary diffusion on spectrogram","author":"ono","year":"2008","journal-title":"Proc of European Signal Processing Conference (EUSIPCO)"},{"key":"ref9","first-page":"1628","article-title":"Phase-based harmonic percussive separation","author":"cano","year":"2014","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref1","author":"comon","year":"2010","journal-title":"Handbook of Blind Source Separation Independent Component Analysis and Applications"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081520"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-53547-0_31","article-title":"The 2016 Signal Separation Evaluation Campaign","author":"liutkus","year":"2017","journal-title":"International Conference on Latent Variable Analysis and Signal Separation (LVA\/ICA)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2811540"},{"key":"ref24","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","article-title":"Twin Networks: Matching the future for sequence generation","author":"serdyuk","year":"2018","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"}],"event":{"name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","location":"Tokyo, Japan","start":{"date-parts":[[2018,9,17]]},"end":{"date-parts":[[2018,9,20]]}},"container-title":["2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8500052\/8521237\/08521371.pdf?arnumber=8521371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T13:14:42Z","timestamp":1643202882000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8521371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iwaenc.2018.8521371","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}