{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T19:34:13Z","timestamp":1769283253148,"version":"3.49.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3396648","type":"journal-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T19:21:45Z","timestamp":1714764105000},"page":"1304-1308","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Vocal Melody Extraction With Multilevel Contexts"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2306-1503","authenticated-orcid":false,"given":"Xian","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2016.1182191"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952660"},{"key":"ref3","first-page":"63","article-title":"Deep salience representations for F0 estimation in polyphonic music","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Bittner","year":"2017"},{"key":"ref4","first-page":"1","article-title":"Melody extraction using a harmonic convolutional neural network","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Balhar","year":"2019"},{"key":"ref5","first-page":"82","article-title":"Main melody estimation with source-filter NMF and CRNN","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Basaran","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189313"},{"key":"ref8","first-page":"819","article-title":"Melody extraction on vocal segments using multi-column deep neural networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Kum","year":"2016"},{"key":"ref9","first-page":"737","article-title":"Singing voice melody transcription using deep neural networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Rigaud","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462420"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023231"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053059"},{"key":"ref13","first-page":"396","article-title":"SpecTNT: A time-frequency transformer for music audio","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Lu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3080625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app9071324"},{"key":"ref16","first-page":"521","article-title":"Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Lu","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413444"},{"key":"ref18","first-page":"93","article-title":"Semi-supervised learning using teacher-student models for vocal melody extraction","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Kum","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747304"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747629"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683630"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461483"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030298"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.108605"},{"key":"ref25","first-page":"1","article-title":"Towards improving harmonic sensitivity and prediction stability for singing melody extraction","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Shao","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2494"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-528"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2188515"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959926"},{"key":"ref30","first-page":"1","article-title":"A Matlab toolbox for efficient perfect reconstruction time-frequency transforms with log-frequency resolution","volume-title":"Proc. AES Int. Conf. Semantic Audio","author":"Schrkhuber","year":"2014"},{"key":"ref31","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Rep.","author":"Yu","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref33","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Bittner","year":"2014"},{"key":"ref34","article-title":"Polyphonic melody extraction","author":"Poliner","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2009.2026503"},{"key":"ref36","first-page":"287","article-title":"RWC music database: Popular, classical and jazz music databases","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Goto","year":"2002"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Rep.","author":"Kingma","year":"2015"},{"key":"ref38","first-page":"1","article-title":"mir_eval: A transparent implementation of common MIR metrics","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Raffel","year":"2014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-8373-9"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10518111.pdf?arnumber=10518111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T17:45:51Z","timestamp":1715622351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10518111\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3396648","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}