{"id":"https://openalex.org/W4413368317","doi":"https://doi.org/10.1007/978-3-032-02548-7_16","title":"Synthesising Cross-Speaker Data for\u00a0Low-Resource Pathological Speech Recognition with\u00a0PEFT","display_name":"Synthesising Cross-Speaker Data for\u00a0Low-Resource Pathological Speech Recognition with\u00a0PEFT","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413368317","doi":"https://doi.org/10.1007/978-3-032-02548-7_16"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-02548-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-032-02548-7_16","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119366466","display_name":"Kesego Mokgosi","orcid":"https://orcid.org/0009-0000-5713-2002"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Kesego Mokgosi","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Milad Dadgar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Milad Dadgar","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028464565","display_name":"Cathy Ennis","orcid":"https://orcid.org/0000-0002-1274-5347"},"institutions":[{"id":"https://openalex.org/I157286207","display_name":"National University of Ireland, Maynooth","ror":"https://ror.org/048nfjm95","country_code":"IE","type":"education","lineage":["https://openalex.org/I157286207"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Cathy Ennis","raw_affiliation_strings":["Maynooth University, Maynooth, Ireland"],"affiliations":[{"raw_affiliation_string":"Maynooth University, Maynooth, Ireland","institution_ids":["https://openalex.org/I157286207"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075345326","display_name":"Robert M. Ross","orcid":"https://orcid.org/0000-0001-8711-1675"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Robert Ross","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5119366466"],"corresponding_institution_ids":["https://openalex.org/I4210144925"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35668362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.8331974744796753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7686895728111267},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6717698574066162},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5221008062362671},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4140404462814331},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36277055740356445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34038710594177246},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07108956575393677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331974744796753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7686895728111267},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6717698574066162},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5221008062362671},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4140404462814331},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36277055740356445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34038710594177246},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07108956575393677}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-02548-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-02548-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W98096188","https://openalex.org/W2018363392","https://openalex.org/W2156279557","https://openalex.org/W2955174253","https://openalex.org/W2992384298","https://openalex.org/W3139237097","https://openalex.org/W3167533889","https://openalex.org/W3205644108","https://openalex.org/W4378464823","https://openalex.org/W4385822680","https://openalex.org/W4402111582","https://openalex.org/W4402111659","https://openalex.org/W4402111804","https://openalex.org/W4402115960","https://openalex.org/W4408807695","https://openalex.org/W6637031373","https://openalex.org/W6796581206"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4389984014","https://openalex.org/W1940231550","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,13,32,65,140],"recognition":[2,33],"is":[3,18,127],"essential":[4],"for":[5,10,137],"enhancing":[6],"communication":[7],"and":[8,40,115,133],"accessibility":[9],"individuals":[11],"with":[12,50,81],"impairments,":[14],"yet":[15],"its":[16],"development":[17],"hindered":[19],"by":[20],"a":[21,85,90],"scarcity":[22],"of":[23,87],"robust,":[24],"speaker-specific":[25,56],"datasets.":[26,118],"This":[27],"study":[28],"explores":[29],"low-resource":[30,138],"dysarthric":[31,57],"through":[34],"cross-speaker":[35],"transfer":[36],"using":[37],"synthetic":[38,120],"data":[39,80,121],"parameter-efficient":[41],"fine-tuning":[42,83,100],"(PEFT).":[43],"We":[44],"integrate":[45],"SpeechT5":[46],"text-to-speech":[47],"(TTS)":[48],"synthesis":[49],"x-vector":[51],"speaker":[52,134],"embeddings":[53],"to":[54,129],"generate":[55],"speech,":[58],"enabling":[59],"model":[60,96],"adaptation":[61],"while":[62],"preserving":[63],"pathological":[64,139],"characteristics":[66],"such":[67],"as":[68],"prosodic":[69],"irregularities.":[70],"Experiments":[71],"on":[72,112],"the":[73,94,101],"TORGO":[74],"dataset":[75],"show":[76],"that":[77],"mixed":[78],"cross-synthetic":[79],"LoRA":[82],"achieves":[84],"WER":[86],"0.17,":[88],"representing":[89],"71.7%":[91],"improvement":[92],"over":[93],"standard":[95],"(0.60":[97],"WER)":[98],"without":[99],"TTS":[102],"model.":[103],"However,":[104],"cross-dataset":[105,131],"generalisation":[106,132],"remains":[107],"challenging,":[108],"yielding":[109],"higher":[110],"WERs":[111],"MINDS-14":[113],"(4.69)":[114],"AMI":[116],"(0.96\u20133.83)":[117],"Whilst":[119],"enhances":[122],"in-domain":[123],"recognition,":[124],"further":[125],"research":[126],"needed":[128],"improve":[130],"adaptation,":[135],"particularly":[136],"settings.":[141]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}