{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:49:26Z","timestamp":1774162166280,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659612","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:11:49Z","timestamp":1552950709000},"page":"1620-1625","source":"Crossref","is-referenced-by-count":5,"title":["Deep Learning Models for Melody Perception: An Investigation on Symbolic Music Data"],"prefix":"10.23919","author":[{"given":"Wei-Tsung","family":"Lu","sequence":"first","affiliation":[]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"ECCV"},{"key":"ref32","article-title":"Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning","author":"lu","year":"2018","journal-title":"ISMIR"},{"key":"ref31","first-page":"1","article-title":"Separating voices in polyphonic music: A contig mapping approach","author":"chew","year":"2004","journal-title":"Proc Int Symp Computer Music Modeling and Retrieval"},{"key":"ref30","author":"chen","year":"2018","journal-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation"},{"key":"ref36","article-title":"mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref35","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2188515"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.07.001"},{"key":"ref12","author":"mauch","year":"0","journal-title":"Computer-aided melody note transcription using the tony software Accuracy and efficiency"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952166"},{"key":"ref14","author":"molina","year":"2014","journal-title":"Evaluation framework for automatic singing transcription"},{"key":"ref15","first-page":"461","article-title":"Musical note estimation for f0 trajectories of singing voices based on a bayesian semi-beat-synchronous hmm","author":"nishikimi","year":"2016","journal-title":"ISMIR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/03640210701864089"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2015.1136650"},{"key":"ref18","first-page":"782","article-title":"A neural greedy model for voice separation in symbolic music","author":"gray","year":"2016","journal-title":"ISMIR"},{"key":"ref19","article-title":"Horizontal and vertical integration\/segregation in auditory streaming: a voice separation algorithm for symbolic musical data","author":"karydis","year":"2007","journal-title":"Proc 4th Sound Music Comput (SMC) Conf"},{"key":"ref28","first-page":"1362","article-title":"Deepbach: a steerable model for bach chorales generation","author":"hadjeres","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"137","article-title":"Pitch analysis for active music discovery","author":"salamon","year":"2016","journal-title":"Machine learning for music discovery workshop international conference on machine learning (icml)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3758\/BF03210494"},{"key":"ref3","article-title":"Search effectiveness measures for symbolic music queries in very large databases","author":"sapp","year":"2004","journal-title":"ISMIR"},{"key":"ref6","first-page":"737","article-title":"Singing voice melody transcription using deep neural networks","author":"rigaud","year":"2016","journal-title":"ISMIR"},{"key":"ref29","author":"chen","year":"2017","journal-title":"Rethinking atrous convolution for semantic image segmentation"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-679"},{"key":"ref7","article-title":"Deep salience representations for fo estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"18th Int Soc for Music Info Retrieval Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/313238.313293"},{"key":"ref9","first-page":"500","article-title":"Melody extraction by contour classification","author":"bittner","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/217279.215273"},{"key":"ref20","first-page":"42","article-title":"Musical voice integration\/segregation: Visa revisited","author":"rafailidis","year":"2009","journal-title":"6th Sound and Music Computing Conference"},{"key":"ref22","first-page":"493","article-title":"Comparing voice and stream segmentation algorithms","author":"guiomard-kagan","year":"2015","journal-title":"International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref21","author":"makris","year":"2016","journal-title":"Visa3 Refining the voice integration\/segregation algorithm"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2001.19.1.1"},{"key":"ref23","article-title":"Improving voice separation by better connecting contigs","author":"guiomard-kagan","year":"2016","journal-title":"International Society for Music Information Retrieval Conference (ISMIR 2016)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1037\/h0094150"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.1914084"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Honolulu, HI, USA","start":{"date-parts":[[2018,11,12]]},"end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659612.pdf?arnumber=8659612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:54:15Z","timestamp":1598244855000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659612","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}