{"id":"https://openalex.org/W4377000501","doi":"https://doi.org/10.1109/taslp.2023.3277290","title":"PQG-A2SA: Performance Quantification Guided Audio-to-Score Alignment for Orchestral Music","display_name":"PQG-A2SA: Performance Quantification Guided Audio-to-Score Alignment for Orchestral Music","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377000501","doi":"https://doi.org/10.1109/taslp.2023.3277290"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3277290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277290","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5025198698","display_name":"Zhicheng Lian","orcid":"https://orcid.org/0000-0003-0736-4598"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhicheng Lian","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065017752","display_name":"Haonan Cheng","orcid":"https://orcid.org/0000-0003-3407-4318"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Cheng","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086311840","display_name":"Jiawan Zhang","orcid":"https://orcid.org/0000-0002-0667-6744"},"institutions":[{"id":"https://openalex.org/I2800287464","display_name":"State Administration of Cultural Heritage","ror":"https://ror.org/04d0vc473","country_code":"CN","type":"government","lineage":["https://openalex.org/I2800287464"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawan Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China","Tianjin Cultural Heritage Conservation and Inheritance Engineering Technology Center and Key Research Center for Surface Monitoring and Analysis of Relics, State Administration of Cultural Heritage, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Cultural Heritage Conservation and Inheritance Engineering Technology Center and Key Research Center for Surface Monitoring and Analysis of Relics, State Administration of Cultural Heritage, China","institution_ids":["https://openalex.org/I2800287464"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025198698"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.4075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54478873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"1982","last_page":"1992"},"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":0.9980999827384949,"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":0.9968000054359436,"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/chord","display_name":"Chord (peer-to-peer)","score":0.8459518551826477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7437500357627869},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6433918476104736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6156253218650818},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5804482102394104},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4580923020839691},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3955349624156952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37886232137680054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3259340226650238},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08389416337013245}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.8459518551826477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437500357627869},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6433918476104736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6156253218650818},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5804482102394104},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4580923020839691},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3955349624156952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37886232137680054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3259340226650238},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08389416337013245},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3277290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277290","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3139283728","display_name":null,"funder_award_id":"62201524","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6130214876","display_name":null,"funder_award_id":"62172295","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8595334750","display_name":null,"funder_award_id":"CUC22GZ002","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W96816272","https://openalex.org/W178108385","https://openalex.org/W1489504608","https://openalex.org/W1510799621","https://openalex.org/W1601211340","https://openalex.org/W1970724543","https://openalex.org/W1973976810","https://openalex.org/W1978295651","https://openalex.org/W2001562039","https://openalex.org/W2079403773","https://openalex.org/W2108494558","https://openalex.org/W2113217465","https://openalex.org/W2125935583","https://openalex.org/W2127265017","https://openalex.org/W2140304104","https://openalex.org/W2146302296","https://openalex.org/W2151131438","https://openalex.org/W2161472614","https://openalex.org/W2206887674","https://openalex.org/W2295112129","https://openalex.org/W2296201206","https://openalex.org/W2402262802","https://openalex.org/W2403476706","https://openalex.org/W2404274215","https://openalex.org/W2476446632","https://openalex.org/W2522399191","https://openalex.org/W2728379535","https://openalex.org/W2764251778","https://openalex.org/W2770705789","https://openalex.org/W2774066932","https://openalex.org/W2889798470","https://openalex.org/W2953788158","https://openalex.org/W3117303186","https://openalex.org/W3125095875","https://openalex.org/W3162873781","https://openalex.org/W3183561830","https://openalex.org/W6603920068","https://openalex.org/W6607429947","https://openalex.org/W6629134104","https://openalex.org/W6679084306","https://openalex.org/W6696946461","https://openalex.org/W6697237593","https://openalex.org/W6713352359","https://openalex.org/W6713534251","https://openalex.org/W6745704996","https://openalex.org/W6746018928","https://openalex.org/W6746709544","https://openalex.org/W6764787368"],"related_works":["https://openalex.org/W2373148193","https://openalex.org/W3134670663","https://openalex.org/W4297791980","https://openalex.org/W2133554502","https://openalex.org/W2137414850","https://openalex.org/W2121755799","https://openalex.org/W2039049596","https://openalex.org/W2108945853","https://openalex.org/W1979781676","https://openalex.org/W635786290"],"abstract_inverted_index":{"Audio-to-score":[0],"alignment":[1,72,91,96,172],"is":[2,22,36,138],"a":[3,37,86,142],"multi-modal":[4],"task":[5],"that":[6],"aims":[7],"at":[8,101,200],"generating":[9],"an":[10,110,122],"accurate":[11],"mapping":[12,144],"between":[13,145],"symbolic":[14,146],"and":[15,28,50,121,126,147,159,179,194],"signal-level":[16],"representations":[17,149],"of":[18,39,61,65,77,150,181],"musical":[19,151,165],"signals,":[20],"which":[21],"important":[23],"for":[24,98],"music":[25,32,35,40,51,76,100],"performance":[26,43,63,87],"analysis":[27,180],"retrieval.":[29],"Among":[30],"numerous":[31],"genres,":[33],"orchestral":[34,66,75,99],"category":[38],"with":[41,94,203],"complex":[42],"characteristics":[44,64],"such":[45],"as":[46],"multi-instrument,":[47],"non-percussive":[48],"instrument":[49],"expressiveness.":[52],"However,":[53],"previous":[54,132],"methods":[55],"do":[56],"not":[57],"take":[58],"sufficient":[59],"account":[60],"the":[62,104,131,134,154,157,171,204],"music,":[67],"leading":[68],"to":[69,140],"limitations":[70],"in":[71,190,196],"accuracy":[73,97],"on":[74],"these":[78],"methods.":[79,206],"To":[80],"solve":[81],"this":[82],"problem,":[83],"we":[84],"present":[85],"quantification":[88],"guided":[89,115,124],"audio-to-score":[90],"(PQG-A2SA)":[92],"method":[93,186],"high":[95],"note-level.":[102],"Specially,":[103],"PQG-A2SA":[105,185],"contains":[106],"two":[107],"parts,":[108],"namely":[109],"Inter":[111],"Onset":[112],"Interval":[113],"(IOI)":[114],"conditionally-constrained":[116,136],"Dynamic":[117],"Time":[118],"Wrapping":[119],"(DTW)":[120],"articulation":[123],"onset":[125,158,191],"offset":[127,160,197],"detection.":[128],"Different":[129],"from":[130],"work,":[133],"IOI-guided":[135],"DTW":[137],"designed":[139],"achieve":[141],"preliminary":[143],"chord-level":[148],"signals.":[152],"In":[153],"second":[155],"module,":[156],"detection":[161],"model":[162],"under":[163],"different":[164],"articulations":[166],"are":[167],"established,":[168],"thus":[169],"refining":[170],"results.":[173],"We":[174],"provide":[175],"extensive":[176],"experimental":[177],"validation":[178],"our":[182],"method.":[183],"Our":[184],"can":[187],"improve":[188],"9.0%":[189],"align":[192,198],"rate":[193,199],"17.5%":[195],"most":[201],"compared":[202],"state-of-the-art":[205]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}