{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T17:13:36Z","timestamp":1770138816224,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682605","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"166-170","source":"Crossref","is-referenced-by-count":21,"title":["Polyphonic Music Transcription with Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Yu-Te","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"63","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref11","article-title":"Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning","author":"lu","year":"2018","journal-title":"Proc ISMIR"},{"key":"ref12","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","year":"2018","journal-title":"Proc ISMIR"},{"key":"ref13","article-title":"Multitask learning for fundamental frequency estimation in music","author":"bittner","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462079"},{"key":"ref15","first-page":"393","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":"Proc ISMIR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661210"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2442411"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018"},{"key":"ref4","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref3","first-page":"234","article-title":"U-Net: Con-volutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159700"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/COMJ_a_00146"},{"key":"ref7","article-title":"An effcient shift-invariant model for polyphonic music transcription","author":"benetos","year":"2013","journal-title":"Proc Int Workshop Machine Learning and Music"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref9","article-title":"Singing voice separation with deep U-Net convolutional networks","author":"jansson","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref22","article-title":"On the potential of simple framewise approaches to piano transcription","author":"kelz","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461686"},{"key":"ref23","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"hawthorne","year":"2018"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682605.pdf?arnumber=8682605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:18:51Z","timestamp":1657840731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682605","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}