{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:59:30Z","timestamp":1730343570160,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"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":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10289758","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T13:55:44Z","timestamp":1698846944000},"page":"136-140","source":"Crossref","is-referenced-by-count":0,"title":["DAACI-VoDAn: Improving Vocal Detection with New Data and Methods"],"prefix":"10.23919","author":[{"given":"Helena","family":"Cuesta","sequence":"first","affiliation":[{"name":"Daaci Ltd.,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadine","family":"Kroher","sequence":"additional","affiliation":[{"name":"Time Machine Capital 2 Ltd.,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aggelos","family":"Pikrakis","sequence":"additional","affiliation":[{"name":"Time Machine Capital 2 Ltd.,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stojan","family":"Djordjevic","sequence":"additional","affiliation":[{"name":"Daaci Ltd.,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"321","article-title":"Zero-mean convolutions for level-invariant singing voice detection","author":"schl\u00fcter","year":"2018","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref12","first-page":"121","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"schl\u00fcter","year":"2015","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app9071324"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-636"},{"key":"ref36","first-page":"44","article-title":"Learning to pinpoint singing voice from weakly labeled examples","author":"schl\u00fcter","year":"2017","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref31","first-page":"18","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"mcfee","year":"0","journal-title":"Proc of the Python in Science Conference"},{"key":"ref30","article-title":"Music source separation in the waveform domain","author":"d\u00e9fossez","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-4703-2_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10060358"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/app12157405"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2917225"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2011.6022500"},{"key":"ref1","first-page":"151","article-title":"MSTRE-Net: Multistreaming acoustic modeling for automatic lyrics transcription","author":"demirel","year":"0","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s13673-018-0158-1"},{"key":"ref19","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","volume":"14","author":"bittner","year":"0","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref18","article-title":"Dali: a large dataset of synchronized audio, lyrics and notes, automatically created using teacher-student machine learning paradigm","author":"meseguer-brocal","year":"0","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref24","first-page":"287","article-title":"RWC Music Database: Popular, Classical and Jazz Music Databases","author":"goto","year":"0","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref26","article-title":"FMA: A dataset for music analysis","author":"defferrard","year":"0","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref25","first-page":"233","article-title":"Timbre and melody features for the recognition of vocal activity and instrumental solos in polyphonic music","author":"mauch","year":"0","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref20","first-page":"506","article-title":"Revisiting singing voice detection: a quantitative review and the future outlook","author":"lee","year":"2018","journal-title":"Proc of the Intl Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref22","first-page":"310","article-title":"On the improvement of singing voice separation for monaural recordings using the MIR-1K dataset","volume":"18","author":"hsu","year":"0","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/e24010114"},{"key":"ref28","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874248"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362337"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177944"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855054"},{"key":"ref3","first-page":"1051","article-title":"Improving accompanied flamenco singing voice transcription by combining vocal detection and predominant melody extraction","author":"kroher","year":"2014","journal-title":"Proc of the Intl Computer Music Conference (ICMC)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825108"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969557"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2023,9,4]]},"location":"Helsinki, Finland","end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10289758.pdf?arnumber=10289758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T14:08:20Z","timestamp":1702303700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10289758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10289758","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}