{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:24:47Z","timestamp":1776889487500,"version":"3.51.2"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["JP19H01116"],"award-info":[{"award-number":["JP19H01116"]}]},{"name":"JSPS KAKENHI","award":["JP20K19818"],"award-info":[{"award-number":["JP20K19818"]}]},{"name":"JSPS-CAS Joint Research Program","award":["JPJSBP120197203"],"award-info":[{"award-number":["JPJSBP120197203"]}]},{"name":"Research Grant A of the Tateisi Science and Technology Foundation"},{"name":"Research Grant of Kawai Foundation for Sound Technology and Music"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3072496","type":"journal-article","created":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T01:11:03Z","timestamp":1618362663000},"page":"1687-1701","source":"Crossref","is-referenced-by-count":19,"title":["Time-Domain Audio Source Separation With Neural Networks Based on Multiresolution Analysis"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4385-7170","authenticated-orcid":false,"given":"Tomohiko","family":"Nakamura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihori","family":"Kozuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5617","authenticated-orcid":false,"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0113-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF02476026"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141095289051"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053723"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-805"},{"key":"ref36","article-title":"The MUSDB18 corpus for music separation","author":"rafii","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-6886-9_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160450502"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2904183"},{"key":"ref11","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683800"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1177"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref17","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Computed Assist Intervention"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"ref27","article-title":"Density estimation using real NVP","author":"dinh","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","article-title":"Singing voice separation with deep U-Net convolutional networks","author":"jansson","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref6","first-page":"23","article-title":"Explicit consistency constraints for STFT spectrograms and their application to phase reconstruction","author":"roux","year":"0","journal-title":"Proc Workshop Statist Perceptual Audition"},{"key":"ref29","article-title":"Deep invertible networks","author":"jacobsen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107368"},{"key":"ref1","first-page":"293","article-title":"The 2018 signal separation evaluation campaign","author":"st\u00f6ter","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separation"},{"key":"ref20","first-page":"2627","article-title":"Convolutional Kernel networks","author":"mairal","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.192463"},{"key":"ref21","first-page":"7324","article-title":"Making convolutional networks shift-invariant again","volume":"97","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/acha.1996.0015"},{"key":"ref26","article-title":"Wavelet pooling for convolutional neural networks","author":"williams","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","first-page":"4013","article-title":"Investigation on wavelet basis function of DNN-based time domain audio source separation inspired by multiresolution analysis","author":"kozuka","year":"0","journal-title":"Proc Int Congr Expo Noise Control Eng"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09403999.pdf?arnumber=9403999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:00:23Z","timestamp":1639771223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9403999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3072496","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}