{"id":"https://openalex.org/W4410771268","doi":"https://doi.org/10.1109/icasspw65056.2025.11011033","title":"Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR","display_name":"Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771268","doi":"https://doi.org/10.1109/icasspw65056.2025.11011033"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/251635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032433720","display_name":"Karl El Hajal","orcid":"https://orcid.org/0000-0003-3128-335X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Karl El Hajal","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland,CH-1920"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland,CH-1920","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042970143","display_name":"Enno Hermann","orcid":"https://orcid.org/0000-0001-9945-1140"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Enno Hermann","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland,CH-1920"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland,CH-1920","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026752360","display_name":"Ajinkya Kulkarni","orcid":"https://orcid.org/0000-0003-1423-3676"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ajinkya Kulkarni","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland,CH-1920"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland,CH-1920","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland,CH-1920"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland,CH-1920","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.6118,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82979029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.978600025177002,"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":0.978600025177002,"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":0.9697999954223633,"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":0.9642999768257141,"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/rhythm","display_name":"Rhythm","score":0.8570575714111328},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7854812145233154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6060219407081604},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17083007097244263}],"concepts":[{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.8570575714111328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7854812145233154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060219407081604},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17083007097244263},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/251635","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/251635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/251635","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/251635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2018363392","https://openalex.org/W2096774922","https://openalex.org/W2508408760","https://openalex.org/W2547793174","https://openalex.org/W2888807255","https://openalex.org/W2907121074","https://openalex.org/W2936861580","https://openalex.org/W3209984917","https://openalex.org/W4224931267","https://openalex.org/W4296068414","https://openalex.org/W4385822680","https://openalex.org/W4385823432","https://openalex.org/W4386609311","https://openalex.org/W4389077323","https://openalex.org/W4391833135","https://openalex.org/W4392930622","https://openalex.org/W4402111804","https://openalex.org/W6783867762","https://openalex.org/W6796720528","https://openalex.org/W6847363464","https://openalex.org/W6872832363"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2072492413","https://openalex.org/W2997159972","https://openalex.org/W4296378967","https://openalex.org/W2064134577","https://openalex.org/W2373995729","https://openalex.org/W2157038729","https://openalex.org/W2393707162"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,36,65,85],"recognition":[2],"(ASR)":[3],"systems":[4],"are":[5,115],"well":[6],"known":[7],"to":[8,23,38,67,70],"perform":[9],"poorly":[10],"on":[11,34,63,83],"dysarthric":[12,69],"speech.":[13,29,72],"Previous":[14],"works":[15],"have":[16],"addressed":[17],"this":[18],"by":[19],"speaking":[20,40],"rate":[21],"modification":[22],"reduce":[24],"the":[25,75,92,102],"mismatch":[26],"with":[27,77,105],"typical":[28,71],"Unfortunately,":[30],"these":[31],"approaches":[32],"rely":[33],"transcribed":[35],"data":[37],"estimate":[39],"rates":[41],"and":[42,58,89,112],"phoneme":[43],"durations,":[44],"which":[45],"might":[46],"not":[47],"be":[48],"available":[49,116],"for":[50,99],"unseen":[51],"speakers.":[52],"Therefore,":[53],"we":[54],"combine":[55],"unsupervised":[56],"rhythm":[57,94],"voice":[59],"conversion":[60,95],"methods":[61],"based":[62],"self-supervised":[64],"representations":[66],"map":[68],"We":[73],"evaluate":[74],"outputs":[76],"a":[78],"large":[79],"ASR":[80],"model":[81],"pre-trained":[82],"healthy":[84],"without":[86],"further":[87],"fine-tuning":[88],"find":[90],"that":[91],"proposed":[93],"especially":[96],"improves":[97],"performance":[98],"speakers":[100],"of":[101,109],"Torgo":[103],"corpus":[104],"more":[106],"severe":[107],"cases":[108],"dysarthria.":[110],"Code":[111],"audio":[113],"samples":[114],"at":[117],"https://idiap.github.io/RnV.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}