{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:20Z","timestamp":1776889040590,"version":"3.51.2"},"reference-count":36,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889826","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":3,"title":["Ultra Lightweight Singing Melody Extraction via Combination of Convolution and MLP"],"prefix":"10.1109","author":[{"given":"Jun","family":"Liu","sequence":"first","affiliation":[{"name":"Donghua University,School of Comp. Science & Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangjie","family":"Dong","sequence":"additional","affiliation":[{"name":"Donghua University,School of Comp. Science & Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiubo","family":"Huang","sequence":"additional","affiliation":[{"name":"Donghua University,School of Comp. Science & Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Yu","sequence":"additional","affiliation":[{"name":"Donghua University,School of Comp. Science & Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University,School of Comp. Science & Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11674-2_14"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2409735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178034"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747629"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687424"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462420"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053059"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413444"},{"key":"ref12","first-page":"819","article-title":"Melody extraction on vocal segments using multi-column deep neural networks","volume-title":"Proc. ISMIR","author":"Kum"},{"key":"ref13","first-page":"884","article-title":"Rethinking Singing Voice Separation With Spectral-Temporal Transformer","volume-title":"Proc. APSIPA ASC","author":"Yu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746056"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447953"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3080625"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.086"},{"key":"ref19","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Morphmlp: A self-attention free, mlp-like backbone for image and video","author":"Zhang","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73119-8_7"},{"key":"ref22","article-title":"Dynamixer: A vision MLP architecture with dynamic mixing","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3145427"},{"key":"ref24","article-title":"Hire-mlp: Vision MLP via hierarchical rearrange ment","volume-title":"Proc. CVPR","author":"Guo"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379457"},{"key":"ref27","article-title":"Distilling the Knowledge in a Neural Network","author":"Hinton","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681288"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2442411"},{"issue":"6","key":"ref30","first-page":"1235","article-title":"Spectral analysis us ing generalised cepstrum","volume":"32","author":"Kobayashi","year":"1984","journal-title":"TASLP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1994-275"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282170"},{"key":"ref33","first-page":"30","article-title":"Self-normalizing neural net works","author":"Klambauer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747304"},{"key":"ref35","article-title":"mir eval: A transparent implementation of common mir metrics","volume-title":"Proc. ISMIR","author":"Raffel"},{"key":"ref36","first-page":"63","article-title":"Deep salience representations for f0 estimation in polyphonic music","volume-title":"Proc. ISMIR","author":"Bittner"}],"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\/10889826.pdf?arnumber=10889826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:04Z","timestamp":1774416364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889826","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}