{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:14:52Z","timestamp":1774120492618,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747304","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"621-625","source":"Crossref","is-referenced-by-count":18,"title":["Tonet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music"],"prefix":"10.1109","author":[{"given":"Ke","family":"Chen","sequence":"first","affiliation":[{"name":"University of California San Diego"}]},{"given":"Shuai","family":"Yu","sequence":"additional","affiliation":[{"name":"Fudan University"}]},{"given":"Cheng-i","family":"Wang","sequence":"additional","affiliation":[{"name":"Smule Inc."}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University"}]},{"given":"Taylor","family":"Berg-Kirkpatrick","sequence":"additional","affiliation":[{"name":"University of California San Diego"}]},{"given":"Shlomo","family":"Dubnov","sequence":"additional","affiliation":[{"name":"University of California San Diego"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.3390\/app9071324","article-title":"Joint detection and classification of singing voice melody using convolutional recurrent neural networks","volume":"9","author":"kum","year":"2019","journal-title":"Applied Sciences"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053059"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413444"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747629"},{"key":"ref14","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"0","journal-title":"ISMIR 2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0301006616651953"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462420"},{"key":"ref17","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NeurIPS 2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.1919362"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Music sketchnet: Controllable music generation via factorized representations of pitch and rhythm","author":"chen","year":"0","journal-title":"ISMIR 2020"},{"key":"ref3","article-title":"Controllable monophonic music generation via latent variable disentanglement","author":"chen","year":"2021","journal-title":"Thesis Master of Architecture"},{"key":"ref6","article-title":"Melody extraction on vocal segments using multi-column deep neural networks","author":"kum","year":"0","journal-title":"ISMIR 2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.819950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683630"},{"key":"ref7","article-title":"Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning","author":"lu","year":"0","journal-title":"ISMIR 2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747630"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414458"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/00033798700200311"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLR 2014"},{"key":"ref21","article-title":"Medleydb: A multitrack dataset for annotation-intensive mir research","author":"bittner","year":"0","journal-title":"ISMIR 2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref23","article-title":"mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"0","journal-title":"ISMIR 2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2020.00025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747304.pdf?arnumber=9747304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:38Z","timestamp":1661199098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747304","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}