{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:28Z","timestamp":1774419748913,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889864","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["A Singing Melody Extraction Network Via Self-Distillation and Multi-Level Supervision"],"prefix":"10.1109","author":[{"given":"Ying","family":"Hu","sequence":"first","affiliation":[{"name":"Key Laboratory of Signal Detection and Processing,Urumqi,China"}]},{"given":"Jiabo","family":"Jing","sequence":"additional","affiliation":[{"name":"Key Laboratory of Signal Detection and Processing,Urumqi,China"}]},{"given":"Fan","family":"Li","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Information and Communications Engineering,Xi’an,China"}]},{"given":"Lijun","family":"He","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Information and Communications Engineering,Xi’an,China"}]},{"given":"Li","family":"Lin","sequence":"additional","affiliation":[{"name":"Xinjiang Institute of Electronics Research Shares Co., Ltd,Urumgi,China"}]},{"given":"Wenzhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.086"},{"key":"ref3","first-page":"521","article-title":"Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning","volume-title":"ISMIR","author":"Lu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2409735"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2531284"},{"key":"ref7","first-page":"819","article-title":"Melody extraction on vocal segments using multi-column deep neural networks","volume-title":"ISMIR","author":"Kum"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413444"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3080625"},{"key":"ref11","article-title":"Spectnt: A time-frequency transformer for music audio","author":"Lu","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189313"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680985"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-528"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2494"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747304"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3139001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3067100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02234"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00631"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01052"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2442411"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164454"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282170"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3228042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3225649"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29629"},{"key":"ref32","article-title":"Msd: Multi-self-distillation learning via multi-classifiers within deep neural networks","author":"Luan","year":"2019"},{"key":"ref33","article-title":"Sgdr: Stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2026503"},{"key":"ref35","first-page":"155","article-title":"Medleydb: A multitrack dataset for annotation-intensive mir research","volume-title":"ISMIR","volume":"14","author":"Bittner"},{"key":"ref36","article-title":"Adam: a method for stochastic optimization","volume-title":"Int Conf Learn Represent","author":"Kingma"},{"key":"ref37","first-page":"2014","article-title":"Mir_eval: A transparent implementation of common mir metrics","volume-title":"ISMIR","volume":"10","author":"Raffel"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889864.pdf?arnumber=10889864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:26Z","timestamp":1774416266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889864","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}