{"id":"https://openalex.org/W4224918098","doi":"https://doi.org/10.1109/icassp43922.2022.9746239","title":"Neural Audio-To-Score Music Transcription For Unconstrained Polyphony Using Compact Output Representations","display_name":"Neural Audio-To-Score Music Transcription For Unconstrained Polyphony Using Compact Output Representations","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918098","doi":"https://doi.org/10.1109/icassp43922.2022.9746239"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746239","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5102447217","display_name":"Victor Arroyo","orcid":null},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Victor Arroyo","raw_affiliation_strings":["University of Alicante,University Institute for Computing Research (IUII),Spain","University Institute for Computing Research (IUII), University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,University Institute for Computing Research (IUII),Spain","institution_ids":["https://openalex.org/I130194489"]},{"raw_affiliation_string":"University Institute for Computing Research (IUII), University of Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080444506","display_name":"Jose J. Valero-Mas","orcid":"https://orcid.org/0000-0001-8667-4070"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose J. Valero-Mas","raw_affiliation_strings":["University of Alicante,University Institute for Computing Research (IUII),Spain","University Institute for Computing Research (IUII), University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,University Institute for Computing Research (IUII),Spain","institution_ids":["https://openalex.org/I130194489"]},{"raw_affiliation_string":"University Institute for Computing Research (IUII), University of Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085151278","display_name":"Jorge Calvo-Zaragoza","orcid":"https://orcid.org/0000-0003-3183-2232"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jorge Calvo-Zaragoza","raw_affiliation_strings":["University of Alicante,University Institute for Computing Research (IUII),Spain","University Institute for Computing Research (IUII), University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,University Institute for Computing Research (IUII),Spain","institution_ids":["https://openalex.org/I130194489"]},{"raw_affiliation_string":"University Institute for Computing Research (IUII), University of Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039304044","display_name":"Antonio Pertusa","orcid":"https://orcid.org/0000-0002-9445-5529"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Pertusa","raw_affiliation_strings":["University of Alicante,University Institute for Computing Research (IUII),Spain","University Institute for Computing Research (IUII), University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,University Institute for Computing Research (IUII),Spain","institution_ids":["https://openalex.org/I130194489"]},{"raw_affiliation_string":"University Institute for Computing Research (IUII), University of Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102447217"],"corresponding_institution_ids":["https://openalex.org/I130194489"],"apc_list":null,"apc_paid":null,"fwci":0.6145,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63696682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4603","last_page":"4607"},"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":0.9987000226974487,"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":0.9986000061035156,"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/polyphony","display_name":"Polyphony","score":0.9176316261291504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209184765815735},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6002748608589172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5771881937980652},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5356075167655945},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5110970139503479},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5031179785728455},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5003452301025391},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4489330053329468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39939796924591064},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3947030305862427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1355150043964386}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9176316261291504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209184765815735},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6002748608589172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5771881937980652},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5356075167655945},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5110970139503479},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5031179785728455},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5003452301025391},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4489330053329468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39939796924591064},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3947030305862427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1355150043964386},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746239","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W60920252","https://openalex.org/W1752772649","https://openalex.org/W1987514054","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2577545569","https://openalex.org/W2771644120","https://openalex.org/W2791445697","https://openalex.org/W2902303903","https://openalex.org/W2981402174","https://openalex.org/W3044620871","https://openalex.org/W3081837312","https://openalex.org/W3145471005","https://openalex.org/W3160132431","https://openalex.org/W3180393551","https://openalex.org/W4288088848","https://openalex.org/W6602461980","https://openalex.org/W6637898492","https://openalex.org/W6687566353","https://openalex.org/W6732146819"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2340483794","https://openalex.org/W2132597408"],"abstract_inverted_index":{"Neural":[0,73],"Audio-to-Score":[1],"(A2S)":[2],"Music":[3],"Transcription":[4],"systems":[5],"have":[6],"shown":[7],"promising":[8],"results":[9],"with":[10,63,76,92,113],"pieces":[11],"containing":[12],"a":[13,41,58,70,106],"fixed":[14],"number":[15,116],"of":[16,37,117],"voices.":[17,118],"However,":[18],"they":[19],"still":[20],"exhibit":[21],"fundamental":[22],"limitations":[23],"that":[24],"constrain":[25],"their":[26],"applicability":[27],"in":[28],"wider":[29],"scenarios.":[30],"This":[31,66],"work":[32],"aims":[33],"at":[34],"tackling":[35],"two":[36],"them:":[38],"we":[39,56],"introduce":[40],"novel":[42],"output":[43],"representation":[44],"which":[45,98],"addresses":[46],"shortcomings":[47],"related":[48],"to":[49,61],"the":[50],"sequence-based":[51],"A2S":[52,81,110],"recognition":[53],"framework":[54],"and":[55,89],"report":[57],"first":[59],"approximation":[60],"dealing":[62,112],"unconstrained":[64,115],"polyphony.":[65],"is":[67],"validated":[68],"on":[69],"Convolutional":[71],"Recurrent":[72],"Network":[74],"(CRNN)":[75],"Connectionist":[77],"Temporal":[78],"Classification":[79],"(CTC)":[80],"scheme":[82],"using":[83],"synthetic":[84],"audio":[85],"from":[86],"string":[87],"quartets":[88],"piano":[90],"sonatas":[91],"intricate":[93],"polyphonic":[94],"mixtures.":[95],"Our":[96],"results,":[97],"improve":[99],"fixed-polyphony":[100],"state-of-the-art":[101],"rates,":[102],"may":[103],"be":[104],"considered":[105],"reference":[107],"for":[108],"future":[109],"works":[111],"an":[114]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
