{"id":"https://openalex.org/W4319862229","doi":"https://doi.org/10.1109/slt54892.2023.10023085","title":"Weak-Supervised Dysarthria-Invariant Features for Spoken Language Understanding Using an Fhvae and Adversarial Training","display_name":"Weak-Supervised Dysarthria-Invariant Features for Spoken Language Understanding Using an Fhvae and Adversarial Training","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862229","doi":"https://doi.org/10.1109/slt54892.2023.10023085"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023085","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023085","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/retrieve/25f0d611-56e1-4e30-94f7-a1fc9d5a2b29","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067760152","display_name":"Jinzi Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jinzi Qi","raw_affiliation_strings":["KULeuven,Department Electrical Engineering-ESAT-PSI,Leuven,Belgium","Department Electrical Engineering-ESAT-PSI, KULeuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KULeuven,Department Electrical Engineering-ESAT-PSI,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department Electrical Engineering-ESAT-PSI, KULeuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["KULeuven,Department Electrical Engineering-ESAT-PSI,Leuven,Belgium","Department Electrical Engineering-ESAT-PSI, KULeuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KULeuven,Department Electrical Engineering-ESAT-PSI,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department Electrical Engineering-ESAT-PSI, KULeuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.207,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36952293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"30","issue":null,"first_page":"375","last_page":"381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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/dysarthria","display_name":"Dysarthria","score":0.8685865998268127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6815730333328247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6624295115470886},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6520810723304749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5305875539779663},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4643350839614868},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4375725984573364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.389040470123291},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22676441073417664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1391199231147766}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.8685865998268127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6815730333328247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6624295115470886},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6520810723304749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5305875539779663},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4643350839614868},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4375725984573364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.389040470123291},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22676441073417664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1391199231147766},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt54892.2023.10023085","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023085","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/705928","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/705928","pdf_url":"https://lirias.kuleuven.be/retrieve/25f0d611-56e1-4e30-94f7-a1fc9d5a2b29","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"9th IEEE workshop on spoken language technology - SLT 2022, Doha, Qatar, 9-12 January 2023","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/705928","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/705928","pdf_url":"https://lirias.kuleuven.be/retrieve/25f0d611-56e1-4e30-94f7-a1fc9d5a2b29","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"9th IEEE workshop on spoken language technology - SLT 2022, Doha, Qatar, 9-12 January 2023","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G1889355044","display_name":null,"funder_award_id":"C24M/22/025","funder_id":"https://openalex.org/F4320322308","funder_display_name":"KU Leuven"}],"funders":[{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320335227","display_name":"Bijzonder Onderzoeksfonds UGent","ror":"https://ror.org/00cv9y106"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319862229.pdf","grobid_xml":"https://content.openalex.org/works/W4319862229.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1520968739","https://openalex.org/W2018363392","https://openalex.org/W2157423596","https://openalex.org/W2758785877","https://openalex.org/W2798571323","https://openalex.org/W2963134917","https://openalex.org/W2963417023","https://openalex.org/W2963703618","https://openalex.org/W2964108264","https://openalex.org/W2964525587","https://openalex.org/W2987573151","https://openalex.org/W3097777922","https://openalex.org/W3142434946","https://openalex.org/W3197516274","https://openalex.org/W3198715519","https://openalex.org/W3198806843","https://openalex.org/W3198861366","https://openalex.org/W3201225328","https://openalex.org/W3216759837","https://openalex.org/W4239396298","https://openalex.org/W4296070216","https://openalex.org/W4385245566","https://openalex.org/W4387682382","https://openalex.org/W6631194405","https://openalex.org/W6743446608","https://openalex.org/W6745117592","https://openalex.org/W6755207826","https://openalex.org/W6801611209"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W3160456149","https://openalex.org/W4239608382","https://openalex.org/W2517018229","https://openalex.org/W2351669973","https://openalex.org/W2168872498","https://openalex.org/W2012360718","https://openalex.org/W83647027","https://openalex.org/W94802903","https://openalex.org/W4246396837"],"abstract_inverted_index":{"The":[0,102],"scarcity":[1],"of":[2,21],"training":[3,79],"data":[4,90],"and":[5,17,61,87,95,113],"the":[6,32,39,68,82,85,129],"large":[7],"speaker":[8,19,62,96],"variation":[9],"in":[10,58,71],"dysarthric":[11,27,45,88,94],"speech":[12,33,89],"lead":[13],"to":[14,80,126],"poor":[15,18],"accuracy":[16,117],"generalization":[20,41],"spoken":[22],"language":[23],"understanding":[24],"systems":[25],"for":[26],"speech.":[28],"Through":[29],"work":[30,65],"on":[31,37,107,118],"features,":[34],"we":[35,76],"focus":[36],"improving":[38],"model":[40,132],"ability":[42],"with":[43,121],"limited":[44],"data.":[46],"Factorized":[47],"Hierarchical":[48],"Variational":[49],"Auto-Encoders":[50],"(FHVAE)":[51],"trained":[52],"unsupervisedly":[53],"have":[54],"shown":[55],"their":[56],"advantage":[57],"disentangling":[59],"content":[60],"representations.":[63],"Earlier":[64],"showed":[66],"that":[67],"dysarthria":[69,124],"shows":[70],"both":[72],"feature":[73],"vectors.":[74],"Here,":[75],"add":[77],"adversarial":[78],"bridge":[81],"gap":[83],"between":[84],"control":[86],"domains.":[91],"We":[92],"extract":[93],"invariant":[97],"features":[98,104,127],"using":[99],"weak":[100],"supervision.":[101],"extracted":[103],"are":[105],"evaluated":[106],"a":[108,115],"Spoken":[109],"Language":[110],"Understanding":[111],"task":[112],"yield":[114],"higher":[116],"unseen":[119],"speakers":[120],"more":[122],"severe":[123],"compared":[125],"from":[128],"basic":[130],"FHVAE":[131],"or":[133],"plain":[134],"filterbanks.":[135]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-31T07:19:18.363097","created_date":"2025-10-10T00:00:00"}