{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T03:49:26Z","timestamp":1769917766224,"version":"3.49.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T00:00:00Z","timestamp":1694908800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T00:00:00Z","timestamp":1694908800000},"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":[[2023,9,17]]},"DOI":"10.1109\/mlsp55844.2023.10285863","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:55:41Z","timestamp":1698083741000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Exploiting Music Source Separation For Singing Voice Detection"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Bonzi","sequence":"first","affiliation":[{"name":"Musixmatch"}]},{"given":"Michele","family":"Mancusi","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}]},{"given":"Simone Del","family":"Deo","sequence":"additional","affiliation":[{"name":"Musixmatch"}]},{"given":"Pierfrancesco","family":"Melucci","sequence":"additional","affiliation":[{"name":"Musixmatch"}]},{"given":"Maria Stella","family":"Tavella","sequence":"additional","affiliation":[{"name":"Musixmatch"}]},{"given":"Loreto","family":"Parisi","sequence":"additional","affiliation":[{"name":"Musixmatch"}]},{"given":"Emanuele","family":"Rodol\u00e1","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Music source separation in the waveform domain","author":"d\u00e9fossez","year":"2019"},{"key":"ref12","article-title":"Hybrid spectrogram and waveform source separation","author":"d\u00e9fossez","year":"2021","journal-title":"Proceedings of the ISMIR 2021 Workshop on Music Source Separation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.79"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume":"abs 2010 11929","author":"dosovitskiy","year":"2020","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091458"},{"key":"ref10","article-title":"Transfer learning for music classification and regression tasks","volume":"abs 1703 9179","author":"choi","year":"2017","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1220847"},{"key":"ref1","article-title":"Lyrics-toaudio alignment and its application","author":"fujihara","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref17","article-title":"Attention is all you need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref16","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume":"abs 1506 4214","author":"shi","year":"2015","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.3390\/app6060162","article-title":"Metrics for polyphonic sound event detection","volume":"6","author":"mesaros","year":"2016","journal-title":"Applied Sciences"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177944"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362337"},{"key":"ref9","article-title":"Automatic tagging using deep convolutional neural networks","volume":"abs 1606 298","author":"choi","year":"2016","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413774"},{"key":"ref6","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"schl\u00fcter","year":"2015","journal-title":"ISMIR"},{"key":"ref5","article-title":"Revisiting singing voice detection: a quantitative review and the future outlook","volume":"abs 1806 1180","author":"lee","year":"2018","journal-title":"CoRR"}],"event":{"name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Rome, Italy","start":{"date-parts":[[2023,9,17]]},"end":{"date-parts":[[2023,9,20]]}},"container-title":["2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10285838\/10285858\/10285863.pdf?arnumber=10285863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:20Z","timestamp":1699902200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,17]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/mlsp55844.2023.10285863","relation":{},"subject":[],"published":{"date-parts":[[2023,9,17]]}}}