{"id":"https://openalex.org/W4402111659","doi":"https://doi.org/10.21437/interspeech.2024-1231","title":"Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition: Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data","display_name":"Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition: Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111659","doi":"https://doi.org/10.21437/interspeech.2024-1231"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1231","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/8175cfbd-0248-4341-9cd9-90a009192c9f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071701468","display_name":"Spyretta Leivaditi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Spyretta Leivaditi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310822","display_name":"Tatsunari Matsushima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsunari Matsushima","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090819693","display_name":"Matt Coler","orcid":"https://orcid.org/0000-0002-7631-5063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matt Coler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001110193","display_name":"Shekhar Nayak","orcid":"https://orcid.org/0000-0002-4277-4851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shekhar Nayak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Vass Verkhodanova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vass Verkhodanova","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071701468"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9363,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75822968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1295","last_page":"1299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9929999709129333,"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":0.9929999709129333,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9545999765396118,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9409000277519226,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7764365673065186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6725501418113708},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5696380138397217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35463231801986694}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7764365673065186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725501418113708},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5696380138397217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35463231801986694}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-1231","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/8175cfbd-0248-4341-9cd9-90a009192c9f","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/8175cfbd-0248-4341-9cd9-90a009192c9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Leivaditi, S, Matsushima, T, Coler, M, Nayak, S & Verkhodanova, V 2024, Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition : Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data. in Proceedings of Interspeech 2024. ISCA, pp. 1295-1299, Interspeech 2024, Kos, Greece, 01/09/2024. https://doi.org/10.21437/interspeech.2024-1231","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:publications/8175cfbd-0248-4341-9cd9-90a009192c9f","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/8175cfbd-0248-4341-9cd9-90a009192c9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Leivaditi, S, Matsushima, T, Coler, M, Nayak, S & Verkhodanova, V 2024, Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition : Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data. in Proceedings of Interspeech 2024. ISCA, pp. 1295-1299, Interspeech 2024, Kos, Greece, 01/09/2024. https://doi.org/10.21437/interspeech.2024-1231","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/8175cfbd-0248-4341-9cd9-90a009192c9f","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/8175cfbd-0248-4341-9cd9-90a009192c9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Leivaditi, S, Matsushima, T, Coler, M, Nayak, S & Verkhodanova, V 2024, Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition : Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data. in Proceedings of Interspeech 2024. ISCA, pp. 1295-1299, Interspeech 2024, Kos, Greece, 01/09/2024. https://doi.org/10.21437/interspeech.2024-1231","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"advancements":[2],"in":[3,68,87],"automatic":[4],"speech":[5,16,35,91,103],"recognition":[6],"technology":[7],"(ASR)":[8],"the":[9,27,54,78,105,111,125],"performance":[10],"of":[11,29,49,64,80],"such":[12,50],"systems":[13],"on":[14],"dysarthric":[15,34,90,100],"is":[17,26],"still":[18],"inadequate":[19],"for":[20,70,133],"widespread":[21],"use.":[22],"One":[23],"key":[24],"reason":[25],"lack":[28],"sufficiently":[30],"rich":[31],"and":[32,47,76,101,110,118],"diverse":[33],"datasets":[36],"to":[37],"train":[38],"machine":[39],"learning":[40,66],"models":[41],"that":[42],"could":[43],"handle":[44],"all":[45],"types":[46],"varieties":[48],"speech.":[51],"Motivated":[52],"by":[53,61],"data":[55,109],"scarcity":[56],"problem,":[57],"as":[58,60],"well":[59],"successful":[62],"applications":[63],"self-supervised":[65],"(SSL)":[67],"ASR":[69],"low-resource":[71],"languages,":[72],"this":[73],"paper":[74],"investigates":[75],"evaluates":[77],"effectiveness":[79],"three":[81],"different":[82],"data-centric":[83],"SSL":[84],"training":[85],"strategies":[86,120],"improving":[88],"Dutch":[89],"recognition.":[92],"The":[93,116],"first":[94,117],"strategy":[95],"involves":[96],"fine-tuning":[97],"with":[98,107,113],"both":[99],"healthy":[102],"data,":[104],"second":[106,126],"disease-specific":[108],"third":[112,119],"speaker-specific":[114],"data.":[115],"are":[121],"proven":[122],"effective,":[123],"while":[124],"one,":[127],"though":[128],"ineffective,":[129],"provides":[130],"valuable":[131],"insights":[132],"further":[134],"research.<br/><br/>":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}