{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:26:31Z","timestamp":1767338791322},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/waspaa.2019.8937135","type":"proceedings-article","created":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T06:50:13Z","timestamp":1577170213000},"page":"160-164","source":"Crossref","is-referenced-by-count":14,"title":["Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer"],"prefix":"10.1109","author":[{"given":"Tomoyasu","family":"Nakano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Nishikimi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kin Wah","family":"Edward Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masataka","family":"Goto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"178","article-title":"Singing voice separation and pitch extraction from monaural polyphonic audio music via DNN and adaptive pitch tracking","author":"fan","year":"2016","journal-title":"BigMM"},{"key":"ref11","first-page":"61","article-title":"Deep clustering and conventional networks for music separation: Stronger together","author":"luo","year":"2017","journal-title":"ICASSP"},{"key":"ref12","first-page":"745","article-title":"Singing voice separation with deep U-Net convolutional networks","author":"jansson","year":"2017","journal-title":"ISMIR"},{"key":"ref13","first-page":"330","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2017","journal-title":"ISMIR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"ref15","first-page":"1","article-title":"Singing voice separation using a deep convolutional neural network trained by ideal binary mask and cross entropy","author":"lin","year":"2018","journal-title":"Neural Computing and Applications"},{"key":"ref16","first-page":"329","article-title":"Jointly detecting and separating singing voice: A multi-task approach","author":"stoller","year":"2018","journal-title":"LVA\/ICA"},{"key":"ref17","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MIC-CAI"},{"key":"ref18","article-title":"Singing voice separation from stereo recordings using spatial clues and robust F0 estimation","author":"caba\u00f1as-molero","year":"2011","journal-title":"AECT conference"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2182510"},{"key":"ref28","first-page":"367","article-title":"mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"ISMIR"},{"key":"ref4","first-page":"737","article-title":"Singing voice melody transcription using deep neural networks","author":"rigaud","year":"2016","journal-title":"ISMIR"},{"key":"ref27","first-page":"287","article-title":"RWC music database: Popular, classical, and jazz music databases","author":"goto","year":"2002","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"ref6","first-page":"82","article-title":"Main melody extraction with source-filter nmf and crnn","author":"basaran","year":"2018","journal-title":"ISMIR"},{"key":"ref5","first-page":"63","article-title":"Deep salience representations for F0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"ISMIR"},{"key":"ref8","first-page":"477","article-title":"Singing-voice separation from monaural recordings using deep recurrent neural networks","author":"huang","year":"2014","journal-title":"ISMIR"},{"key":"ref7","first-page":"521","article-title":"Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning","author":"lu","year":"2018","journal-title":"ISMIR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178348"},{"key":"ref1","first-page":"514","article-title":"Vocals in music matter: the relevance of vocals in the minds of listeners","author":"demetriou","year":"2018","journal-title":"ISMIR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158801"},{"key":"ref22","first-page":"1976","article-title":"Neural network adaptive beamforming for robust multichannel speech recognition","author":"li","year":"2016","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-92"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764276"},{"key":"ref26","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"2014","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref25","first-page":"1","article-title":"Adam: A method for stochastic opti-mization","author":"kingma","year":"2015","journal-title":"ICLRE"}],"event":{"name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2019,10,20]]},"location":"New Paltz, NY, USA","end":{"date-parts":[[2019,10,23]]}},"container-title":["2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8932990\/8937073\/08937135.pdf?arnumber=8937135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:21Z","timestamp":1657854621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8937135\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/waspaa.2019.8937135","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}