{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T05:21:11Z","timestamp":1777526471862,"version":"3.51.4"},"reference-count":119,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3216282","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:05:56Z","timestamp":1667513156000},"page":"113850-113864","source":"Crossref","is-referenced-by-count":10,"title":["PipaSet and TEAS: A Multimodal Dataset and Annotation Platform for Automatic Music Transcription and Expressive Analysis Dedicated to Chinese Traditional Plucked String Instrument Pipa"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2382-3424","authenticated-orcid":false,"given":"Yuancheng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2098-5823","authenticated-orcid":false,"given":"Yuyang","family":"Jing","sequence":"additional","affiliation":[{"name":"Nanjing University of the Art, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3666-2738","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"Conservatory of Music, XiaoZhuang University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorian","family":"Cazau","sequence":"additional","affiliation":[{"name":"Laboratory-STICC, UMR 6285, Brest, CNRS, Institute of Mines-T&#x00E9;l&#x00E9;com Atlantique, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5192-982X","authenticated-orcid":false,"given":"Olivier","family":"Adam","sequence":"additional","affiliation":[{"name":"UMR7190, CNRS, Institute of Jean Le Rond d&#x2019;Alembert, Sorbonne Univerisity, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-0472","authenticated-orcid":false,"given":"Qiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","year":"0","journal-title":"No 561 Product of the Shanghai no 1 National Musical Instrument Factory Pipa Used in This Paper"},{"key":"ref38","first-page":"301","article-title":"De-centering the west: East Asian philosophies and the ethics of applying artificial intelligence to music","author":"huang","year":"2021","journal-title":"Proc ISMIR"},{"key":"ref33","first-page":"239","article-title":"Automatically identifying vocal expressions for music transcription","author":"miryala","year":"2013","journal-title":"Proc ISMIR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2174227"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2014.922999"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref37","first-page":"678","article-title":"Automatic music transcription and ethnomusicology: A user study","author":"holzapfel","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref36","first-page":"69","article-title":"Computational ethnomusicology: A music information retrieval perspective","author":"tzanetakis","year":"2014","journal-title":"Proc ICMC"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2016.1233285"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.4930187"},{"key":"ref28","first-page":"71","article-title":"Estimation of guitar fingering and plucking controls based on multimodal analysis of motion, audio and musical score","author":"alfonso","year":"2015","journal-title":"Proc Symp CMMR"},{"key":"ref27","article-title":"Multimodal music information retrieval: From content analysis to multimodal fusion","author":"zhonghua","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref20","first-page":"809","article-title":"Adaptive time-frequency scattering for modulation recognition in music signal","author":"wang","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref22","year":"2022","journal-title":"CompMusic Workshop 2022 Introduction to Computational Musicology a Carnatic Music Perspective"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053474"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366618"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8707-4_5"},{"key":"ref101","first-page":"24741","article-title":"Neural human performer: Learning generalizable radiance fields for human performance rendering","author":"kwon","year":"2021","journal-title":"Proc Neurlps"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00012"},{"key":"ref100","article-title":"Multi-view video-based 3D hand pose estimation","author":"khaleghi","year":"2021","journal-title":"arXiv 2109 11747"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66881-9_11"},{"key":"ref50","first-page":"453","article-title":"GuitarSet: A dataset for guitar transcription","author":"xi","year":"2018","journal-title":"Proc ISMIR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178036"},{"key":"ref58","year":"0","journal-title":"Premiere Pro Video Editing Software"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2761348"},{"key":"ref56","article-title":"Detection and tracking of point features","author":"tomasi","year":"1991"},{"key":"ref55","year":"0","journal-title":"RME Fireface UFX Sound Card"},{"key":"ref54","year":"0","journal-title":"sE Electronics sE8 Small Diaphragm Microphone"},{"key":"ref53","first-page":"1","article-title":"Information retrieval of Marovany zither music with an original optical-based system","author":"cazau","year":"2013","journal-title":"Proc DAFx"},{"key":"ref52","first-page":"1","article-title":"Hexaphonic guitar transcription and visualization","author":"angulo","year":"2016","journal-title":"Proc TENOR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7110-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/0929821042000317840"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199659647.001.0001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.57"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2868887"},{"key":"ref49","first-page":"309","article-title":"Escaping from the Abyss of manual annotation: New methodology of building polyphonic datasets for automatic music transcription","author":"su","year":"2015","journal-title":"Proc CMMR Symp"},{"key":"ref7","article-title":"Computational modeling of musical expression perspectives, datasets, analysis and generation","author":"cancino-chac\u00f3n","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811739.014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683408"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2162816"},{"key":"ref48","first-page":"1","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"2019","journal-title":"Proc ICLR"},{"key":"ref47","first-page":"69","article-title":"Towards automated extraction of tempo parameters from expressive recordings","author":"m\u00fcller","year":"2009","journal-title":"Proc ISMIR"},{"key":"ref42","author":"zhuang","year":"2001","journal-title":"Pipa Handbook"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WIAMIS.2013.6616120"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1121\/1.390533"},{"key":"ref43","year":"0","journal-title":"ZPshen Pipa Fonts"},{"key":"ref73","first-page":"107","article-title":"Vibrato extraction and parameterization in the spectral modeling synthesis framework","author":"herrera","year":"1998","journal-title":"Proc DAFx Workshop"},{"key":"ref72","first-page":"823","article-title":"Score-informed analysis of intonation and pitch modulation in jazz solos","author":"abe\u00dfer","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref71","article-title":"Creating music by listening","author":"jehan","year":"2005"},{"key":"ref70","first-page":"361","article-title":"Local group delay based vibrato and tremolo suppression for onset detection","author":"b\u00f6ck","year":"2013","journal-title":"Proc ISMIR"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1080\/17459737.2016.1263897"},{"key":"ref77","first-page":"365","article-title":"A voice activity detector employing soft decision based noise spectrum adaptation","author":"sohn","year":"1998","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ISCCSP.2012.6217808"},{"key":"ref75","first-page":"8476","article-title":"Vibrato detection using cross correlation between temporal energy and fundamental frequency","volume":"1","author":"coler","year":"2011","journal-title":"Proc AESC"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857806"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20603-5_16"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref62","year":"0","journal-title":"Celemony Melodyne Studio 5"},{"key":"ref61","first-page":"23","article-title":"Computer-aided melody note transcription using the Tony software: Accuracy and efficiency","author":"mauch","year":"2015","journal-title":"Proc TENOR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930917"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760529"},{"key":"ref66","author":"antoniou","year":"2007","journal-title":"Practical Optimization Algorithms and Engineering Applications"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853843"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"key":"ref2","year":"0","journal-title":"Music information retrieval evaluation exchange (Mirex)"},{"key":"ref69","first-page":"4","article-title":"Maximum filter vibrato suppression for onset detection","volume":"7","author":"b\u00f6ck","year":"2013","journal-title":"Proc DAFx"},{"key":"ref1","article-title":"On the segmentation and analysis of continuous musical sound by digital computer","author":"moorer","year":"1975"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref95","first-page":"71","article-title":"An analysis\/synthesis framework for automatic F0 annotation of multitrack datasets","author":"salamon","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref108","article-title":"A comprehensive survey on cross-modal retrieval","author":"wang","year":"2016","journal-title":"arXiv 1607 06215"},{"key":"ref94","doi-asserted-by":"crossref","DOI":"10.17918\/etd-3806","article-title":"Analysis and synthesis of expressive guitar performance","author":"migneco","year":"2012"},{"key":"ref107","first-page":"431","article-title":"JosquIntab: A dataset for content-based computational analysis of music in lute tablature","author":"valk","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref93","first-page":"239","article-title":"Template-based vibrato analysis in complex music signals","author":"driedger","year":"2016","journal-title":"Proc ISMIR"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3397499"},{"key":"ref92","first-page":"63","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0004-6"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042119"},{"key":"ref104","first-page":"123","article-title":"Video-based vibrato detection and analysis for polyphonic string music","author":"li","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref90","first-page":"637","article-title":"music21: A toolkit for computer-aided musicology and symbolic music data","author":"cuthbert","year":"2010","journal-title":"Proc ISMIR"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4711699"},{"key":"ref102","first-page":"1","article-title":"Visual pitch estimation","author":"koepke","year":"2019","journal-title":"Proc SMC"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053115"},{"key":"ref110","first-page":"809","article-title":"Analysis of expressive musical terms in violin using score-informed and expression-based audio features","author":"li","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref98","first-page":"406","article-title":"Hierarchical evaluation of segment boundary detection","author":"mcfee","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2820691"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.2307\/40285257"},{"key":"ref97","article-title":"A tutorial on deep learning for music information retrieval","author":"choi","year":"2017","journal-title":"arXiv 1709 04396"},{"key":"ref10","first-page":"1","article-title":"Left and right-hand guitar playing techniques detection","author":"reboursi\u00e8re","year":"2013","journal-title":"Proc NIME"},{"key":"ref11","first-page":"708","article-title":"Electric guitar playing technique detection in real world recordings based on F0 sequence pattern recognition","author":"chen","year":"2015","journal-title":"Proc ISMIR"},{"key":"ref12","first-page":"9","article-title":"Sparse cepstral, phase codes for guitar playing technique classification","author":"su","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref13","first-page":"219","article-title":"Automatic tablature transcription of electric guitar recordings by estimation of score- and instrument-related parameters","author":"kehling","year":"2014","journal-title":"Proc DAFx"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.23"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2702384"},{"key":"ref118","year":"0","journal-title":"Music XML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959552"},{"key":"ref82","year":"0","journal-title":"Ample China Pipa"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref17","first-page":"108","article-title":"AVA: An interactive system for visual and quantitative analyses of vibrato and portamento performance styles","author":"yang","year":"2016","journal-title":"Proc ISMIR"},{"key":"ref81","year":"0","journal-title":"Intelligent Sound Processing (ISP) Toolbox"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2020.1784957"},{"key":"ref84","year":"2013","journal-title":"National General Textbook for Social Art Grade Examination for Pipa"},{"key":"ref119","year":"0","journal-title":"MIDI Polyphonic Expression"},{"key":"ref19","first-page":"85","article-title":"Joint analysis of mode and playing technique in Guqin performance with machine learning","author":"huang","year":"2020","journal-title":"Proc ISMIR"},{"key":"ref83","first-page":"5522","article-title":"Cyclic tempogram&#x2014;A mid-level tempo representation for musicsignals","author":"peter","year":"2010","journal-title":"Proc IEEE ICASSP"},{"key":"ref114","first-page":"604","article-title":"Query by video: Cross-modal music retrieval","author":"li","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref113","first-page":"115","article-title":"Learning audio-sheet music correspondences for score identification and offline alignment","author":"dorfer","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1049\/icp.2021.1460"},{"key":"ref80","first-page":"329","article-title":"Study of the tremolo technique on the acoustic guitar: Experimental setup and preliminary results on regularity","author":"freire","year":"2013","journal-title":"Proc SMC"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1121\/1.4790351"},{"key":"ref89","first-page":"1","article-title":"MIDI-DDSP: Detailed control of musical performance via hierarchical modeling","author":"wu","year":"2022","journal-title":"Proc ICLR"},{"key":"ref85","year":"2012","journal-title":"The Collection for Pipa Grade Examination of China"},{"key":"ref86","first-page":"1","article-title":"Music performance analysis: A survey","author":"lerch","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3359852.3359898"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00016"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09926100.pdf?arnumber=9926100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:12:22Z","timestamp":1733883142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9926100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":119,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3216282","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}