{"id":"https://openalex.org/W7130830562","doi":"https://doi.org/10.31449/inf.v50i6.12075","title":"Fine-Tuning OpenAI Whisper-Small for Domain-Specific Medical Speech Recognition within a Microservice Architecture","display_name":"Fine-Tuning OpenAI Whisper-Small for Domain-Specific Medical Speech Recognition within a Microservice Architecture","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7130830562","doi":"https://doi.org/10.31449/inf.v50i6.12075"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i6.12075","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i6.12075","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/12075/6470","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.informatica.si/index.php/informatica/article/download/12075/6470","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052166927","display_name":"Alaeddine Moussa","orcid":null},"institutions":[{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Alaeddine Moussa","raw_affiliation_strings":["Universit\u00e9 de la Manouba, \u00c9cole Nationale des Sciences de l\u2019Informatique, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de la Manouba, \u00c9cole Nationale des Sciences de l\u2019Informatique, Tunisia","institution_ids":["https://openalex.org/I83259278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126559176","display_name":"Noursene Drine","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Noursene Drine","raw_affiliation_strings":["Universite de Tunis El Manar, \u00c9cole Nationale des Sciences de l\u2019Informatique, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Tunis El Manar, \u00c9cole Nationale des Sciences de l\u2019Informatique, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I63596082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052166927"],"corresponding_institution_ids":["https://openalex.org/I83259278"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29258186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.1665000021457672,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.1665000021457672,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.13760000467300415,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.043800000101327896,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5110999941825867},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49129998683929443},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.47510001063346863},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4390000104904175},{"id":"https://openalex.org/keywords/systems-architecture","display_name":"Systems architecture","score":0.33250001072883606},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884999871253967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6323000192642212},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2646999955177307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i6.12075","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i6.12075","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/12075/6470","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v50i6.12075","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i6.12075","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/12075/6470","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6456966996192932,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130830562.pdf","grobid_xml":"https://content.openalex.org/works/W7130830562.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,54],"fine-tune":[1],"Whisper-small":[2,22],"(244M":[3],"parameters)":[4],"on":[5],"8.5":[6],"hours":[7],"of":[8],"in-domain":[9],"medical":[10],"audio":[11],"and":[12,61],"evaluatewith":[13],"word":[14],"error":[15],"rate":[16],"(WER).":[17],"Compared":[18],"to":[19,30],"an":[20,58],"unadapted":[21],"baseline,":[23],"our":[24],"fine-tuned":[25],"modelreduces":[26],"WER":[27],"from":[28],"\u223c63%":[29],"\u223c32%.":[31],"While":[32],"the":[33,48],"relative":[34],"gain":[35],"is":[36,40],"substantial,":[37],"this":[38],"accuracy":[39],"not":[41],"suitablefor":[42],"unsupervised":[43],"clinical":[44],"use\u037e":[45],"we":[46],"position":[47],"system":[49],"as":[50,57],"a":[51],"clinician-in-the-loop":[52],"assistant.":[53],"also":[55],"describedeployment":[56],"on-premise":[59],"microservice":[60],"report":[62],"latency/throughput":[63],"considerations.":[64]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-22T00:00:00"}
