{"id":"https://openalex.org/W4372338351","doi":"https://doi.org/10.1109/icassp49357.2023.10094733","title":"Frame-Level Multi-Label Playing Technique Detection Using Multi-Scale Network and Self-Attention Mechanism","display_name":"Frame-Level Multi-Label Playing Technique Detection Using Multi-Scale Network and Self-Attention Mechanism","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338351","doi":"https://doi.org/10.1109/icassp49357.2023.10094733"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5087938991","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/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/A5015592602","display_name":"Wenwu Meng","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":"Wenwu Meng","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/A5043561002","display_name":"Yulun Wu","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":"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/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["National Institute of Informatics (NII),Digital Content and Media Sciences Research Division,Japan","Digital Content and Media Sciences Research Division, National Institute of Informatics (NII), Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics (NII),Digital Content and Media Sciences Research Division,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics (NII), Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107394203","display_name":"Fan Xia","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":"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":"last","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"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":7,"corresponding_author_ids":["https://openalex.org/A5087938991"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.4075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54153365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8086363077163696},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.620067298412323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5526517033576965},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5377220511436462},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5259725451469421},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5042983293533325},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4805482029914856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45890870690345764},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.45382675528526306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4401947557926178},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4150296747684479},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4137292802333832},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3234850764274597},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.05991825461387634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086363077163696},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.620067298412323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526517033576965},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5377220511436462},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5259725451469421},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5042983293533325},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4805482029914856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45890870690345764},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.45382675528526306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4401947557926178},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4150296747684479},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4137292802333832},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3234850764274597},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.05991825461387634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2036197063","https://openalex.org/W2053347927","https://openalex.org/W2191779130","https://openalex.org/W2296756383","https://openalex.org/W2394782790","https://openalex.org/W2744337652","https://openalex.org/W2807788374","https://openalex.org/W2885570506","https://openalex.org/W2937941430","https://openalex.org/W2958623036","https://openalex.org/W2980716541","https://openalex.org/W2991362318","https://openalex.org/W3014641072","https://openalex.org/W3095303521","https://openalex.org/W3184475559","https://openalex.org/W4211256381","https://openalex.org/W4223638755","https://openalex.org/W4296567412","https://openalex.org/W4385245566","https://openalex.org/W6696841990","https://openalex.org/W6712094209","https://openalex.org/W6739901393","https://openalex.org/W6743221894","https://openalex.org/W6753544557","https://openalex.org/W6761545431","https://openalex.org/W6769284903","https://openalex.org/W6771324532","https://openalex.org/W6799327274","https://openalex.org/W6843182537"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2385132419","https://openalex.org/W2772780115","https://openalex.org/W2114557664","https://openalex.org/W2546942002"],"abstract_inverted_index":{"Instrument":[0],"playing":[1],"technique":[2],"(IPT)":[3],"is":[4],"a":[5,51,61,68,89,96,141],"key":[6],"element":[7],"of":[8,13,82],"musical":[9],"presentation.":[10],"However,":[11],"most":[12],"the":[14,117,122,126,131],"existing":[15,138],"works":[16,139],"for":[17],"IPT":[18,80,148],"detection":[19],"only":[20],"concern":[21],"monophonic":[22],"music":[23],"signals,":[24],"yet":[25],"little":[26],"has":[27],"been":[28],"done":[29],"to":[30,59,99,121],"detect":[31],"IPTs":[32,40,87],"in":[33,91,147],"polyphonic":[34],"instrumental":[35],"solo":[36],"pieces":[37],"with":[38],"overlapping":[39],"or":[41],"mixed":[42],"IPTs.":[43],"In":[44],"this":[45,101],"paper,":[46],"we":[47,94],"formulate":[48],"it":[49,58],"as":[50],"frame-level":[52],"multi-label":[53],"classification":[54],"problem":[55,102],"and":[56,76,106,116],"apply":[57],"Guzheng,":[60],"Chinese":[62],"plucked":[63],"string":[64],"instrument.":[65],"We":[66],"create":[67],"new":[69,97],"dataset,":[70],"Guzheng":[71,74],"Tech99,":[72],"containing":[73],"recordings":[75],"onset,":[77],"offset,":[78],"pitch,":[79],"annotations":[81],"each":[83],"note.":[84],"Because":[85],"different":[86,114],"vary":[88],"lot":[90],"their":[92],"lengths,":[93],"propose":[95],"method":[98],"solve":[100],"using":[103],"multi-scale":[104,109],"network":[105,110],"self-attention.":[107],"The":[108],"extracts":[111],"features":[112],"from":[113],"scales,":[115],"self-attention":[118],"mechanism":[119],"applied":[120],"feature":[123,133],"maps":[124],"at":[125],"coarsest":[127],"scale":[128],"further":[129],"enhances":[130],"long-range":[132],"extraction.":[134],"Our":[135],"approach":[136],"outperforms":[137],"by":[140],"large":[142],"margin,":[143],"indicating":[144],"its":[145],"effectiveness":[146],"detection.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}