{"id":"https://openalex.org/W4415432871","doi":"https://doi.org/10.21437/interspeech.2025-2099","title":"WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper","display_name":"WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432871","doi":"https://doi.org/10.21437/interspeech.2025-2099"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2099","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5115616824","display_name":"Emmanuel Akinrintoyo","orcid":"https://orcid.org/0000-0002-9343-2958"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Emmanuel Akinrintoyo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092596232","display_name":"Nadine Abdelhalim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nadine Abdelhalim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076361939","display_name":"Nicole Salomons","orcid":"https://orcid.org/0000-0003-4319-8419"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicole Salomons","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115616824"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16642247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1413","last_page":"1417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.4921000003814697,"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/T12031","display_name":"Speech and dialogue systems","score":0.4921000003814697,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.47929999232292175,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dementia","display_name":"Dementia","score":0.7491000294685364},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5034000277519226},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5005000233650208},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3912000060081482},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.35440000891685486},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.32350000739097595}],"concepts":[{"id":"https://openalex.org/C2779483572","wikidata":"https://www.wikidata.org/wiki/Q83030","display_name":"Dementia","level":3,"score":0.7491000294685364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7117999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5410000085830688},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.35440000891685486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C2778223994","wikidata":"https://www.wikidata.org/wiki/Q905592","display_name":"Filler (materials)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2099","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/127496","is_oa":false,"landing_page_url":"https://hdl.handle.net/10044/1/127496","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1413","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Whisper":[0,65],"fails":[1],"to":[2,40,77,90,125],"correctly":[3],"transcribe":[4],"dementia":[5,10,49,69],"speech":[6,15,31,50,70,129],"because":[7],"persons":[8],"with":[9,66],"(PwDs)":[11],"often":[12],"exhibit":[13],"irregular":[14],"patterns":[16],"and":[17,23,32,54,73,97,128],"disfluencies":[18],"such":[19],"as":[20],"pauses,":[21],"repetitions,":[22],"fragmented":[24],"sentences.":[25],"It":[26],"was":[27,121],"trained":[28],"on":[29],"standard":[30],"may":[33],"have":[34],"had":[35],"little":[36],"or":[37],"no":[38],"exposure":[39],"dementia-affected":[41],"speech.":[42],"However,":[43],"correct":[44],"transcription":[45],"is":[46],"vital":[47],"for":[48,51],"cost-effective":[52],"diagnosis":[53],"the":[55,67,92,105],"development":[56],"of":[57,114],"assistive":[58],"technology.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"fine-tune":[64],"open-source":[68],"dataset":[71,76],"(DementiaBank)":[72],"our":[74],"in-house":[75],"improve":[78],"its":[79],"word":[80],"error":[81],"rate":[82,95],"(WER).":[83],"The":[84,100,108],"fine-tuning":[85],"also":[86],"includes":[87],"filler":[88,93],"words":[89],"ascertain":[91],"inclusion":[94],"(FIR)":[96],"F1":[98],"score.":[99],"fine-tuned":[101],"models":[102],"significantly":[103],"outperformed":[104],"off-the-shelf":[106],"models.":[107],"medium-sized":[109],"model":[110],"achieved":[111],"a":[112,122],"WER":[113],"0.24,":[115],"outperforming":[116],"previous":[117],"work.":[118],"Similarly,":[119],"there":[120],"notable":[123],"generalisability":[124],"unseen":[126],"data":[127],"patterns.":[130]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
