{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:28Z","timestamp":1740169228449,"version":"3.37.3"},"reference-count":59,"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":[{"DOI":"10.13039\/501100009025","name":"JST ACCEL","doi-asserted-by":"publisher","award":["JPMJAC1602"],"award-info":[{"award-number":["JPMJAC1602"]}],"id":[{"id":"10.13039\/501100009025","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003382","name":"JST CREST","doi-asserted-by":"publisher","award":["JPMJCR20D4"],"award-info":[{"award-number":["JPMJCR20D4"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["19H04137"],"award-info":[{"award-number":["19H04137"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3096819","type":"journal-article","created":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T20:24:15Z","timestamp":1626207855000},"page":"101994-102003","source":"Crossref","is-referenced-by-count":3,"title":["Vocal-Accompaniment Compatibility Estimation Using Self-Supervised and Joint-Embedding Techniques"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3181-4894","authenticated-orcid":false,"given":"Takayuki","family":"Nakatsuka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kento","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3978-1444","authenticated-orcid":false,"given":"Yuki","family":"Koyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3085-7446","authenticated-orcid":false,"given":"Masahiro","family":"Hamasaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masataka","family":"Goto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8859-6539","authenticated-orcid":false,"given":"Shigeo","family":"Morishima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref38","first-page":"255","article-title":"Joint beat and downbeat tracking with recurrent neural networks","author":"b\u00f6ck","year":"2016","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/app9071324"},{"key":"ref31","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref30","first-page":"2930","article-title":"Playing hard exploration games by watching youtube","author":"aytar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref37","first-page":"1","article-title":"Separating musical sources with convolutional sparse coding","author":"dubey","year":"2016","journal-title":"Proc 2nd Int Conf Appl Intell Syst (APPIS)"},{"key":"ref36","first-page":"1","article-title":"TimbreTron: A WaveNet (cycleGAN (CQT (audio))) pipeline for musical timbre transfer","author":"huang","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref35","article-title":"Comparison of time-frequency representations for environmental sound classification using convolutional neural networks","author":"huzaifah","year":"2017","journal-title":"arXiv 1706 07156"},{"key":"ref34","first-page":"63","article-title":"Deep salience representations for $F_{0}$\n estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2868887"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref2","first-page":"399","article-title":"Automatic mashup creation by considering both vertical and horizontal mashabilities","author":"lee","year":"2015","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.30535\/mto.19.3.1"},{"key":"ref20","first-page":"7763","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref22","first-page":"604","article-title":"Query by video: Cross-modal music retrieval","author":"li","year":"2019","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2868428"},{"key":"ref23","first-page":"295","article-title":"Learning a joint embedding space of monophonic and mixed music signals for singing voice","author":"lee","year":"2019","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app10124176"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73603-7_44"},{"key":"ref50","first-page":"1703","author":"craswell","year":"2009","journal-title":"Mean Reciprocal Rank"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367348"},{"journal-title":"The MUSDB18 corpus for music separation","year":"2017","author":"rai","key":"ref59"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.01.013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1236"},{"key":"ref56","first-page":"374","article-title":"Distance measures for speech recognition, psychological and instrumental","volume":"116","author":"mermelstein","year":"1976","journal-title":"Pattern Recognit Artif Intell"},{"journal-title":"An Introduction to Wavelets","year":"1992","author":"chui","key":"ref55"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1049\/ji-1.1947.0015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082307"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123314"},{"key":"ref40","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","author":"sohn","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123394"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350956"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2766898"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964958"},{"key":"ref17","first-page":"464","article-title":"Real-time chord recognition of musical sound: A system using common lisp music","author":"fujishima","year":"1999","journal-title":"Proc Int Comput Music Conf (ICMC)"},{"key":"ref18","first-page":"112","article-title":"Learning classification with unlabeled data","author":"de sa","year":"1994","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2347135"},{"key":"ref3","first-page":"151","article-title":"A hierarchical harmonic mixing method","author":"bernardes","year":"2017","journal-title":"Proc Int Symp Comput Music Multidisciplinary Res (CMMR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4018\/IJACDT.2019070102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app6050123"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref7","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref49","first-page":"446","article-title":"Learning semantic similarity in music via self-supervision","author":"bretan","year":"2019","journal-title":"Proc Int Soc Music Inf Retr (ISMIR) Conf"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref46","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref45","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref47","first-page":"72","article-title":"A unit selection methodology for music generation using deep neural networks","author":"bretan","year":"2017","journal-title":"Proc Int Conf Comput Creativity (ICCC)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973795"},{"journal-title":"LibROSA\/LibROSA 0 7 2 Zenodo","year":"2020","author":"mcfee","key":"ref41"},{"key":"ref44","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09481947.pdf?arnumber=9481947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:01Z","timestamp":1639771021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9481947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3096819","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}