{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:10:33Z","timestamp":1776888633558,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462420","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"371-375","source":"Crossref","is-referenced-by-count":45,"title":["Vocal Melody Extraction Using Patch-Based CNN"],"prefix":"10.1109","author":[{"given":"Li","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2442411"},{"key":"ref12","article-title":"Exploiting frequency, periodicity and harmonicity using advanced time-frequency concentration techniques for multipitch estimation of choir and symphony","author":"su","year":"2016","journal-title":"ISMIR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282170"},{"key":"ref14","article-title":"Automatic music transcription leveraging generalized cepstral features and deep learning","author":"wu","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47292-8_7"},{"key":"ref16","article-title":"Music pitch representation by periodicity measures based on combined temporal and spectral representations","author":"peeters","year":"2006","journal-title":"Proc IEEE ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/89.876309"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.908129"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164416"},{"key":"ref4","article-title":"Deep salience representations for $f_{0}$ estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"18th Int Soc for Music Info Retrieval Conf"},{"key":"ref3","first-page":"737","article-title":"Singing voice melody transcription using deep neural networks","author":"rigaud","year":"2016","journal-title":"ISMIR"},{"key":"ref6","first-page":"500","article-title":"Melody extraction by contour classification","author":"bittner","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2188515"},{"key":"ref2","first-page":"819","article-title":"Melody extraction on vocal segments using multi-column deep neural networks","author":"kum","year":"2016","journal-title":"Proc ISMIR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964292"},{"key":"ref9","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168400"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref21","article-title":"Mel-generalized cepstral analysis: a unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref24","article-title":"mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref23","first-page":"155","article-title":"Medleydb: A multitrack dataset for annotation-intensive mir research","volume":"14","author":"bittner","year":"2014","journal-title":"Proc ISMIR"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462420.pdf?arnumber=8462420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:18:06Z","timestamp":1598231886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462420","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}