{"id":"https://openalex.org/W4415035391","doi":"https://doi.org/10.21437/interspeech.2025-512","title":"Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages","display_name":"Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415035391","doi":"https://doi.org/10.21437/interspeech.2025-512"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-512","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-512","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.14874","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023430268","display_name":"C. H. Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chin-Jou Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110721529","display_name":"Eunjung Yeo","orcid":"https://orcid.org/0009-0003-4452-4084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunjung Yeo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023799668","display_name":"Kwanghee Choi","orcid":"https://orcid.org/0000-0001-5254-1093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwanghee Choi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090347814","display_name":"Paula Andrea P\u00e9rez-Toro","orcid":"https://orcid.org/0000-0002-2727-2116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paula Andrea P\u00e9rez-Toro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030925462","display_name":"Masao Someki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masao Someki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053209750","display_name":"Zhengjun Yue","orcid":"https://orcid.org/0000-0002-1101-549X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengjun Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014414626","display_name":"Juan Rafael Orozco\u2010Arroyave","orcid":"https://orcid.org/0000-0002-8507-0782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Rafael Orozco-Arroyave","raw_affiliation_strings":[],"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":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5023430268"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37123519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2128","last_page":"2132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9977999925613403,"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":0.9977999925613403,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9901000261306763,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9886999726295471,"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/prosody","display_name":"Prosody","score":0.7633000016212463},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48989999294281006},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4269999861717224},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.38260000944137573},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3528999984264374},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3366999924182892}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7633000016212463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7594000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869000196456909},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-512","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-512","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:arXiv.org:2505.14874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14874","pdf_url":"https://arxiv.org/pdf/2505.14874","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.14874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14874","pdf_url":"https://arxiv.org/pdf/2505.14874","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"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":{"Automatic":[0],"speech":[1,6,29,46,71,120],"recognition":[2],"(ASR)":[3],"for":[4,68],"dysarthric":[5,28,70,122],"remains":[7],"challenging":[8],"due":[9],"to":[10,31,42,58],"data":[11,54,114],"scarcity,":[12],"particularly":[13],"in":[14],"non-English":[15,45,49],"languages.":[16],"To":[17],"address":[18],"this,":[19],"we":[20],"fine-tune":[21,59],"a":[22,60],"voice":[23],"conversion":[24,90],"model":[25],"on":[26,74],"English":[27],"(UASpeech)":[30],"encode":[32],"both":[33,86],"speaker":[34,87],"characteristics":[35],"and":[36,79,88,97,104,108],"prosodic":[37],"distortions,":[38],"then":[39,56],"apply":[40],"it":[41],"convert":[43],"healthy":[44],"(FLEURS)":[47],"into":[48],"dysarthric-like":[50],"speech.":[51],"The":[52],"generated":[53,113,119],"is":[55],"used":[57],"multilingual":[61],"ASR":[62],"model,":[63],"Massively":[64],"Multilingual":[65],"Speech":[66],"(MMS),":[67],"improved":[69],"recognition.":[72],"Evaluation":[73],"PC-GITA":[75],"(Spanish),":[76],"EasyCall":[77],"(Italian),":[78],"SSNCE":[80],"(Tamil)":[81],"demonstrates":[82],"that":[83,117],"VC":[84],"with":[85],"prosody":[89],"significantly":[91],"outperforms":[92],"the":[93,112,118],"off-the-shelf":[94],"MMS":[95],"performance":[96],"conventional":[98],"augmentation":[99],"techniques":[100],"such":[101],"as":[102],"speed":[103],"tempo":[105],"perturbation.":[106],"Objective":[107],"subjective":[109],"analyses":[110],"of":[111],"further":[115],"confirm":[116],"simulates":[121],"characteristics.":[123]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
