{"id":"https://openalex.org/W4392909613","doi":"https://doi.org/10.1109/icassp48485.2024.10447162","title":"A Transformer Approach for Polyphonic Audio-to-Score Transcription","display_name":"A Transformer Approach for Polyphonic Audio-to-Score Transcription","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909613","doi":"https://doi.org/10.1109/icassp48485.2024.10447162"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447162","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/A5005281683","display_name":"Mar\u00eda Alfaro-Contreras","orcid":"https://orcid.org/0000-0003-1676-3101"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"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":"Mar\u00eda Alfaro-Contreras","raw_affiliation_strings":["University of Alicante,Pattern Recognition and Artificial Intelligence Group,Spain","Pattern Recognition and Artificial Intelligence Group, University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,Pattern Recognition and Artificial Intelligence Group,Spain","institution_ids":["https://openalex.org/I4210131846"]},{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, University of Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051070601","display_name":"Antonio R\u00edos-Vila","orcid":"https://orcid.org/0000-0002-7770-9726"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"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 R\u00edos-Vila","raw_affiliation_strings":["University of Alicante,Pattern Recognition and Artificial Intelligence Group,Spain","Pattern Recognition and Artificial Intelligence Group, University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,Pattern Recognition and Artificial Intelligence Group,Spain","institution_ids":["https://openalex.org/I4210131846"]},{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, 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/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"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,Pattern Recognition and Artificial Intelligence Group,Spain","Pattern Recognition and Artificial Intelligence Group, University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,Pattern Recognition and Artificial Intelligence Group,Spain","institution_ids":["https://openalex.org/I4210131846"]},{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, University of Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085151278","display_name":"Jorge Calvo-Zaragoza","orcid":"https://orcid.org/0000-0003-3183-2232"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"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,Pattern Recognition and Artificial Intelligence Group,Spain","Pattern Recognition and Artificial Intelligence Group, University of Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alicante,Pattern Recognition and Artificial Intelligence Group,Spain","institution_ids":["https://openalex.org/I4210131846"]},{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, 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/A5005281683"],"corresponding_institution_ids":["https://openalex.org/I130194489","https://openalex.org/I4210131846"],"apc_list":null,"apc_paid":null,"fwci":0.9877,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7218336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"706","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9855999946594238,"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":0.9853000044822693,"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":0.8398412466049194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6525949835777283},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6204165816307068},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5281883478164673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48346859216690063},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1197272539138794},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11038655042648315},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09388419985771179},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07688206434249878}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8398412466049194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6525949835777283},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6204165816307068},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5281883478164673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48346859216690063},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1197272539138794},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11038655042648315},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09388419985771179},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07688206434249878},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447162","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":[],"funders":[{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2572730214","https://openalex.org/W2771644120","https://openalex.org/W2890285072","https://openalex.org/W2902303903","https://openalex.org/W2981402174","https://openalex.org/W3043861921","https://openalex.org/W3044620871","https://openalex.org/W3112478873","https://openalex.org/W3160132431","https://openalex.org/W3180393551","https://openalex.org/W3201139606","https://openalex.org/W4224918098","https://openalex.org/W4385245566","https://openalex.org/W4385822560","https://openalex.org/W6732146819","https://openalex.org/W6733936739","https://openalex.org/W6756884195"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2340483794","https://openalex.org/W2132597408","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"End-to-end":[0],"Audio-to-Score":[1],"(A2S)":[2],"transcription":[3,120],"aims":[4],"to":[5,92,128],"derive":[6],"a":[7,19,79,88],"score":[8],"that":[9],"represents":[10],"the":[11,35,98,112,115,119],"music":[12,110],"content":[13],"of":[14,107,114,125],"an":[15,73,123],"audio":[16,99],"recording":[17],"in":[18],"single":[20],"step.":[21],"While":[22],"current":[23],"state-of-the-art":[24],"methods,":[25],"which":[26,117],"rely":[27],"on":[28,78],"Convolutional":[29],"Recurrent":[30],"Neural":[31],"Networks":[32],"trained":[33],"with":[34,57],"Connectionist":[36],"Temporal":[37],"Classification":[38],"loss":[39],"function,":[40],"have":[41],"shown":[42],"promising":[43],"results":[44,102],"under":[45],"constrained":[46],"circumstances,":[47],"these":[48,68],"approaches":[49],"still":[50],"exhibit":[51],"fundamental":[52],"limitations,":[53],"especially":[54],"when":[55,96],"dealing":[56],"complex":[58],"sequence":[59],"modeling":[60],"tasks,":[61],"such":[62],"as":[63],"polyphonic":[64,108],"music.":[65],"To":[66],"address":[67],"conditions,":[69],"this":[70],"work":[71],"introduces":[72],"alternative":[74],"learning":[75],"scheme":[76],"based":[77],"Transformer":[80],"decoder,":[81],"specifically":[82],"tailored":[83],"for":[84],"A2S":[85],"by":[86,122],"incorporating":[87],"two-dimensional":[89],"positional":[90],"encoding":[91],"preserve":[93],"frequency-time":[94],"relationships":[95],"processing":[97],"signal.":[100],"The":[101],"obtained":[103],"over":[104],"three":[105],"datasets":[106],"string":[109],"confirm":[111],"adequacy":[113],"method,":[116],"improves":[118],"rate":[121],"average":[124],"44%":[126],"compared":[127],"previous":[129],"approaches.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
