{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:58:26Z","timestamp":1782313106589,"version":"3.54.5"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["DFG WE 6611\/1-1"],"award-info":[{"award-number":["DFG WE 6611\/1-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3200547","type":"journal-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T19:48:00Z","timestamp":1661284080000},"page":"2814-2827","source":"Crossref","is-referenced-by-count":11,"title":["Comparing Deep Models and Evaluation Strategies for Multi-Pitch Estimation in Music Recordings"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2143-4679","authenticated-orcid":false,"given":"Christof","family":"Weis","sequence":"first","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5255-3019","authenticated-orcid":false,"given":"Geoffroy","family":"Peeters","sequence":"additional","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412155"},{"key":"ref33","first-page":"216","article-title":"Multiple fundamental frequency estimation by summing harmonic amplitudes","author":"klapuri","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref32","article-title":"MT3: Multi-task multitrack music transcription","author":"gardner","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","first-page":"121","article-title":"Learning multi-pitch estimation from weakly aligned score–audio pairs using a multi-label CTC loss","author":"wei\u00df","year":"0","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959972"},{"key":"ref37","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput - Assist Intervention"},{"key":"ref36","first-page":"63","article-title":"Deep salience representations for F0 tracking in polyphonic music","author":"bittner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.4790351"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref27","article-title":"Saarland music data (SMD)","author":"m\u00fcller","year":"0","journal-title":"Demos Late Breaking News Int Soc Music Inf Retrieval Conf"},{"key":"ref29","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref2","first-page":"34","article-title":"An end-to-end framework for audio-to-score music transcription on monophonic excerpts","author":"rom\u00e1n","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682605"},{"key":"ref22","first-page":"1","article-title":"Jazz bass transcription using a U-net architecture","author":"abe\u00dfer","year":"2021","journal-title":"Electronics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475405"},{"key":"ref24","first-page":"553","article-title":"Development of the RWC music database","author":"goto","year":"0","journal-title":"Proc Int Congr Acoust"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052987"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46282-0_20"},{"key":"ref25","first-page":"239","article-title":"Template-based vibrato analysis of music signals","author":"driedger","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746549"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0250-y"},{"key":"ref11","first-page":"341","article-title":"A closer look on artist filters for musical genre classification","author":"flexer","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00020"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2919","DOI":"10.1109\/TASLP.2020.3030485","article-title":"Local key estimation in music recordings: A case study across songs, versions, and annotators","volume":"28","author":"wei\u00df","year":"2020","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042119"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637776"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/8363507"},{"key":"ref16","first-page":"125","article-title":"Analysis of intonation in unison choir singing","author":"cuesta","year":"0","journal-title":"Proc Int Conf Music Perception Cogn"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3429743","article-title":"Schubert Winterreise dataset: A multimodal scenario for music analysis","volume":"14","author":"wei\u00df","year":"2021","journal-title":"Journal on Computing and Cultural Heritage"},{"key":"ref18","article-title":"Learning features of music from scratch","author":"thickstun","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461686"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030482"},{"key":"ref6","first-page":"50","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref5","first-page":"475","article-title":"On the potential of simple framewise approaches to piano transcription","author":"kelz","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref8","first-page":"246","article-title":"Sequence-to-sequence piano transcription with transformers","author":"hawthorne","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref49","first-page":"1","article-title":"A discriminative model for polyphonic piano transcription","volume":"2007","author":"poliner","year":"2007","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref7","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","first-page":"831","article-title":"Principles of risk minimization for learning theory","author":"vapnik","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","first-page":"746","article-title":"Learning pitch-class representations from score–audio pairs of classical music","author":"wei\u00df","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070851"},{"key":"ref42","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 30 Annu Conf Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533407"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287638"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09865174.pdf?arnumber=9865174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T20:43:43Z","timestamp":1664225023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9865174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3200547","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}