{"id":"https://openalex.org/W7123344213","doi":"https://doi.org/10.1016/j.asoc.2026.114643","title":"Multimodal transformers for image and audio polyphonic music transcription","display_name":"Multimodal transformers for image and audio polyphonic music transcription","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123344213","doi":"https://doi.org/10.1016/j.asoc.2026.114643"},"language":"en","primary_location":{"id":"doi:10.1016/j.asoc.2026.114643","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.114643","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.asoc.2026.114643","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122876741","display_name":"Mar\u00eda Alfaro-Contreras","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mar\u00eda Alfaro-Contreras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122892373","display_name":"Noelia Luna-Barahona","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noelia Luna-Barahona","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-5425-2427","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067125611","display_name":"Carlos P\u00e9rez-Sancho","orcid":"https://orcid.org/0000-0003-1099-7417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos P\u00e9rez-Sancho","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1099-7417","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085151278","display_name":"Jorge Calvo-Zaragoza","orcid":"https://orcid.org/0000-0003-3183-2232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge Calvo-Zaragoza","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3183-2232","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080444506","display_name":"Jose J. Valero-Mas","orcid":"https://orcid.org/0000-0001-8667-4070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose J. Valero-Mas","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8667-4070","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5122876741"],"corresponding_institution_ids":[],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08721405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"191","issue":null,"first_page":"114643","last_page":"114643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.18400000035762787,"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":0.18400000035762787,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.14790000021457672,"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/T10860","display_name":"Speech and Audio Processing","score":0.12020000070333481,"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/transcription","display_name":"Transcription (linguistics)","score":0.7753999829292297},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7099000215530396},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7039999961853027},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3944000005722046},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.33410000801086426}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7753999829292297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494000196456909},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7099000215530396},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7039999961853027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4081999957561493},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37630000710487366},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.33410000801086426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2883000075817108}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.asoc.2026.114643","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.114643","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.asoc.2026.114643","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.114643","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4226433678","display_name":null,"funder_award_id":"PID2023-148259NB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1988273857","https://openalex.org/W2030863126","https://openalex.org/W2087064593","https://openalex.org/W2105143211","https://openalex.org/W2124698093","https://openalex.org/W2619383789","https://openalex.org/W2906214917","https://openalex.org/W2968036310","https://openalex.org/W3004064628","https://openalex.org/W3042456249","https://openalex.org/W3044620871","https://openalex.org/W3112478873","https://openalex.org/W3180393551","https://openalex.org/W3213036384","https://openalex.org/W4223499953","https://openalex.org/W4313594098","https://openalex.org/W4376226279","https://openalex.org/W4380147749","https://openalex.org/W4382602926","https://openalex.org/W4392131573","https://openalex.org/W4401960466","https://openalex.org/W4408851912","https://openalex.org/W4412644084"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2026-01-14T00:00:00"}
