{"id":"https://openalex.org/W4392910303","doi":"https://doi.org/10.1109/icassp48485.2024.10447445","title":"Mertech: Instrument Playing Technique Detection Using Self-Supervised Pretrained Model with Multi-Task Finetuning","display_name":"Mertech: Instrument Playing Technique Detection Using Self-Supervised Pretrained Model with Multi-Task Finetuning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910303","doi":"https://doi.org/10.1109/icassp48485.2024.10447445"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064873117","display_name":"Dichucheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dichucheng Li","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027384378","display_name":"Yinghao Ma","orcid":"https://orcid.org/0000-0002-9984-2229"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yinghao Ma","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076273993","display_name":"Weixing Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixing Wei","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK)"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK)","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456858","display_name":"Yulun Wu","orcid":"https://orcid.org/0000-0001-8085-4951"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulun Wu","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048806438","display_name":"Mingjin Che","orcid":null},"institutions":[{"id":"https://openalex.org/I2799285397","display_name":"Sichuan Conservatory of Music","ror":"https://ror.org/01khb1c27","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799285397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjin Che","raw_affiliation_strings":["Sichuan Conservatory of Music,College of Experimental Art,Sichuan,China","College of Experimental Art, Sichuan Conservatory of Music, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"Sichuan Conservatory of Music,College of Experimental Art,Sichuan,China","institution_ids":["https://openalex.org/I2799285397"]},{"raw_affiliation_string":"College of Experimental Art, Sichuan Conservatory of Music, Sichuan, China","institution_ids":["https://openalex.org/I2799285397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991270","display_name":"Fan Xia","orcid":"https://orcid.org/0000-0001-6644-1376"},"institutions":[{"id":"https://openalex.org/I2799285397","display_name":"Sichuan Conservatory of Music","ror":"https://ror.org/01khb1c27","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799285397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Xia","raw_affiliation_strings":["Sichuan Conservatory of Music,College of Experimental Art,Sichuan,China","College of Experimental Art, Sichuan Conservatory of Music, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"Sichuan Conservatory of Music,College of Experimental Art,Sichuan,China","institution_ids":["https://openalex.org/I2799285397"]},{"raw_affiliation_string":"College of Experimental Art, Sichuan Conservatory of Music, Sichuan, China","institution_ids":["https://openalex.org/I2799285397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009189637","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-9177-4551"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, Fudan University, Shanghai, China","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5064873117"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.0219,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72913686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9679999947547913,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695605754852295},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7450956106185913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5252444744110107},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39856258034706116},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08692976832389832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695605754852295},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7450956106185913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252444744110107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39856258034706116},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08692976832389832},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G201252934","display_name":null,"funder_award_id":"62171138","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2126551001","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320319993","funder_display_name":"Leverhulme Trust"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8793594538","display_name":null,"funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"},{"id":"https://openalex.org/F4320320640","display_name":"Lloyd's Tercentenary Research Foundation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W2408239454","https://openalex.org/W2888806961","https://openalex.org/W2958623036","https://openalex.org/W3035609550","https://openalex.org/W3209059054","https://openalex.org/W4223638755","https://openalex.org/W4224931246","https://openalex.org/W4307323391","https://openalex.org/W4310879273","https://openalex.org/W4319862642","https://openalex.org/W4372338351","https://openalex.org/W4372349783","https://openalex.org/W4379251869","https://openalex.org/W4381710926","https://openalex.org/W4385245566","https://openalex.org/W4388820595","https://openalex.org/W6696841990","https://openalex.org/W6714030504","https://openalex.org/W6743221894","https://openalex.org/W6745851314","https://openalex.org/W6771324532","https://openalex.org/W6802388392","https://openalex.org/W6802842272","https://openalex.org/W6843182537","https://openalex.org/W6846470732","https://openalex.org/W6846805990","https://openalex.org/W6852985890","https://openalex.org/W6853393314"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Instrument":[0],"playing":[1],"techniques":[2],"(IPTs)":[3],"constitute":[4],"a":[5,36,97],"pivotal":[6],"component":[7],"of":[8,14,65,71,76,142],"musical":[9],"expression.":[10],"However,":[11],"the":[12,63,69,74,112,140],"development":[13],"automatic":[15],"IPT":[16,50,80,105,134,147],"detection":[17,51,90],"methods":[18],"suffers":[19],"from":[20],"limited":[21],"labeled":[22],"data":[23,45,56],"and":[24,46,58,73,88,129],"inherent":[25],"class":[26,59],"imbalance":[27,60],"issues.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,82,95],"propose":[33],"to":[34],"apply":[35,96],"self-supervised":[37],"learning":[38],"model":[39],"pre-trained":[40],"on":[41,49,145],"large-scale":[42],"unlabeled":[43],"music":[44],"finetune":[47],"it":[48],"tasks.":[52,93],"This":[53],"approach":[54,99],"addresses":[55],"scarcity":[57],"challenges.":[61],"Recognizing":[62],"significance":[64],"pitch":[66,87],"in":[67,78,118,126],"capturing":[68],"nuances":[70],"IPTs":[72],"importance":[75],"onset":[77,89,113,117],"locating":[79],"events,":[81],"investigate":[83],"multi-task":[84,143],"finetuning":[85,144],"with":[86],"as":[91],"auxiliary":[92],"Additionally,":[94],"post-processing":[98],"for":[100],"event-level":[101,130],"prediction,":[102],"where":[103],"an":[104,108,116],"activation":[106],"initiates":[107],"event":[109],"only":[110],"if":[111],"output":[114],"confirms":[115],"that":[119],"frame.":[120],"Our":[121],"method":[122],"outperforms":[123],"prior":[124],"approaches":[125],"both":[127],"frame-level":[128],"metrics":[131],"across":[132],"multiple":[133],"benchmark":[135],"datasets.":[136],"Further":[137],"experiments":[138],"demonstrate":[139],"efficacy":[141],"each":[146],"class.":[148],"<sup":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
