{"id":"https://openalex.org/W4415432852","doi":"https://doi.org/10.21437/interspeech.2025-2155","title":"Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition","display_name":"Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432852","doi":"https://doi.org/10.21437/interspeech.2025-2155"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2155","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/A5016617263","display_name":"Dominik Wagner","orcid":"https://orcid.org/0000-0002-3631-4138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076479722","display_name":"Ilja Baumann","orcid":"https://orcid.org/0000-0002-1991-3710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilja Baumann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093764","display_name":"Natalie Engert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natalie Engert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113257042","display_name":"Seanie Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seanie Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054443473","display_name":"Elmar N\u00f6th","orcid":"https://orcid.org/0000-0002-3396-555X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmar N\u00f6th","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0351,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96812994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3294","last_page":"3298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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":0.9621000289916992,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9531999826431274,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.566100001335144},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4537999927997589},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4471000134944916},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4431000053882599},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.397599995136261},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7578999996185303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974999904632568},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3125},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2155","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:kobv.de-opus4-th-nuernberg:4355","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/4355","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"our":[5],"submission":[6],"to":[7,25,39,99],"the":[8],"Speech":[9],"Accessibility":[10],"Project":[11],"challenge":[12],"for":[13,46],"dysarthric":[14,41,95],"speech":[15,96],"recognition.":[16],"We":[17],"integrate":[18],"parameter-efficient":[19],"fine-tuning":[20,37,66,106],"with":[21,51,93],"latent":[22],"audio":[23,90],"representations":[24],"improve":[26],"an":[27],"encoder-decoder":[28],"ASR":[29],"system.":[30],"Synthetic":[31],"training":[32],"data":[33],"is":[34],"generated":[35],"by":[36],"Parler-TTS":[38],"mimic":[40],"speech,":[42],"using":[43],"LLM-generated":[44],"prompts":[45],"corpus-consistent":[47],"target":[48],"transcripts.":[49],"Personalization":[50],"x-vectors":[52],"consistently":[53],"reduces":[54],"word":[55],"error":[56],"rates":[57],"(WERs)":[58],"over":[59,104],"non-personalized":[60],"fine-tuning.":[61],"AdaLoRA":[62],"adapters":[63],"outperform":[64],"full":[65],"and":[67,77],"standard":[68],"low-rank":[69],"adaptation,":[70],"achieving":[71],"relative":[72,101],"WER":[73,83,102],"reductions":[74],"of":[75],"\u223c23%":[76],"\u223c22%,":[78],"respectively.":[79],"Further":[80],"improvements":[81],"(\u223c5%":[82],"reduction)":[84],"come":[85],"from":[86],"incorporating":[87],"wav2vec":[88],"2.0-based":[89],"representations.":[91],"Training":[92],"synthetic":[94],"yields":[97],"up":[98],"\u223c7%":[100],"improvement":[103],"personalized":[105],"alone.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}