{"id":"https://openalex.org/W7131730495","doi":"https://doi.org/10.1016/j.csl.2026.101966","title":"Improvements in Spanish audio transcription workflows: Integrating preprocessing, LLM-based correction, and speaker diarization and identification","display_name":"Improvements in Spanish audio transcription workflows: Integrating preprocessing, LLM-based correction, and speaker diarization and identification","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131730495","doi":"https://doi.org/10.1016/j.csl.2026.101966"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2026.101966","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101966","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","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/A5049343684","display_name":"Gonzalo Nieto Montero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149470","display_name":"Fundaci\u00f3n Ram\u00f3n Areces","ror":"https://ror.org/04ra91131","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210149470"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Gonzalo Nieto Montero","raw_affiliation_strings":["Cires21 R&D, P.\u00b0de la Castellana, 81, 15th floor, 28046, Madrid, Spain"],"raw_orcid":"https://orcid.org/0009-0005-4265-1447","affiliations":[{"raw_affiliation_string":"Cires21 R&D, P.\u00b0de la Castellana, 81, 15th floor, 28046, Madrid, Spain","institution_ids":["https://openalex.org/I4210149470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126944987","display_name":"Santiago Hern\u00e1ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149470","display_name":"Fundaci\u00f3n Ram\u00f3n Areces","ror":"https://ror.org/04ra91131","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210149470"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Santiago Hern\u00e1ndez","raw_affiliation_strings":["Cires21 R&D, P.\u00b0de la Castellana, 81, 15th floor, 28046, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cires21 R&D, P.\u00b0de la Castellana, 81, 15th floor, 28046, Madrid, Spain","institution_ids":["https://openalex.org/I4210149470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126915650","display_name":"Juan Casal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149470","display_name":"Fundaci\u00f3n Ram\u00f3n Areces","ror":"https://ror.org/04ra91131","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210149470"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Casal","raw_affiliation_strings":["Cires21 R&D, P.\u00b0de la Castellana, 81, 15th floor, 28046, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cires21 R&D, P.\u00b0de la Castellana, 81, 15th floor, 28046, Madrid, Spain","institution_ids":["https://openalex.org/I4210149470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049343684"],"corresponding_institution_ids":["https://openalex.org/I4210149470"],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19500634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"100","issue":null,"first_page":"101966","last_page":"101966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8876000046730042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8876000046730042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.03500000014901161,"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/T11309","display_name":"Music and Audio Processing","score":0.0272000003606081,"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":0.7602999806404114},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5598999857902527},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46560001373291016},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43160000443458557},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.3774000108242035},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.3587999939918518},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.29100000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769000172615051},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7602999806404114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6431999802589417},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5598999857902527},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.csl.2026.101966","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101966","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5309166312217712}],"awards":[{"id":"https://openalex.org/G6295532458","display_name":null,"funder_award_id":"IDI-20240449","funder_id":"https://openalex.org/F4320321043","funder_display_name":"Centro para el Desarrollo Tecnol\u00f3gico Industrial"}],"funders":[{"id":"https://openalex.org/F4320321043","display_name":"Centro para el Desarrollo Tecnol\u00f3gico Industrial","ror":"https://ror.org/0124x7055"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4383104431","https://openalex.org/W4385274493","https://openalex.org/W4400275805","https://openalex.org/W4408565363"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-02-27T00:00:00"}
