{"id":"https://openalex.org/W4372341972","doi":"https://doi.org/10.1109/icassp49357.2023.10095547","title":"Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition","display_name":"Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341972","doi":"https://doi.org/10.1109/icassp49357.2023.10095547"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software,China","Institute of Software, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shujie Hu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042515126","display_name":"Guinan Li","orcid":"https://orcid.org/0000-0002-2206-0237"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guinan Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9962000250816345,"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/speech-recognition","display_name":"Speech recognition","score":0.7490635514259338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7362382411956787},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5649145841598511},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5186933279037476},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48348814249038696},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.468494713306427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46471914649009705},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4360237121582031},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4332895874977112},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4281888008117676},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4144599735736847},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4126441180706024},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3486754298210144},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07495057582855225}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7490635514259338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362382411956787},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5649145841598511},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5186933279037476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48348814249038696},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.468494713306427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46471914649009705},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4360237121582031},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4332895874977112},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4281888008117676},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4144599735736847},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4126441180706024},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3486754298210144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07495057582855225},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1959608418","https://openalex.org/W1979651826","https://openalex.org/W1989674786","https://openalex.org/W2099621636","https://openalex.org/W2168510624","https://openalex.org/W2239847623","https://openalex.org/W2250686550","https://openalex.org/W2396944218","https://openalex.org/W2401277329","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2752796333","https://openalex.org/W2883586237","https://openalex.org/W2888789389","https://openalex.org/W2889419636","https://openalex.org/W2936771798","https://openalex.org/W2936861580","https://openalex.org/W2943237054","https://openalex.org/W2963799213","https://openalex.org/W2964167449","https://openalex.org/W2972516210","https://openalex.org/W2972956697","https://openalex.org/W3014690389","https://openalex.org/W3034924009","https://openalex.org/W3036601975","https://openalex.org/W3082218567","https://openalex.org/W3095123370","https://openalex.org/W3095930733","https://openalex.org/W3097341038","https://openalex.org/W3097720583","https://openalex.org/W3097909406","https://openalex.org/W3097969370","https://openalex.org/W3125118953","https://openalex.org/W3161294170","https://openalex.org/W3163725792","https://openalex.org/W3174329270","https://openalex.org/W3196511136","https://openalex.org/W3197858274","https://openalex.org/W3197912841","https://openalex.org/W3197943112","https://openalex.org/W3198454118","https://openalex.org/W3198806843","https://openalex.org/W3207399576","https://openalex.org/W4206924127","https://openalex.org/W4221148457","https://openalex.org/W4221156109","https://openalex.org/W4221167580","https://openalex.org/W4225753921","https://openalex.org/W4283461667","https://openalex.org/W4296068414","https://openalex.org/W4296068817","https://openalex.org/W4297841734","https://openalex.org/W4320013936","https://openalex.org/W6603616073","https://openalex.org/W6640963894","https://openalex.org/W6675409298","https://openalex.org/W6687506355","https://openalex.org/W6780218876","https://openalex.org/W6785297517"],"related_works":["https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961"],"abstract_inverted_index":{"Automatic":[0],"recognition":[1],"of":[2,30,135,142,151,156],"disordered":[3,50],"speech":[4,32,51,73],"remains":[5],"a":[6],"highly":[7],"challenging":[8],"task":[9],"to":[10,23,57,70],"date.":[11],"The":[12],"underlying":[13],"neuro-motor":[14],"conditions,":[15],"often":[16],"compounded":[17],"with":[18,112,158],"co-occurring":[19],"physical":[20],"disabilities,":[21],"lead":[22],"the":[24,91,95,103,124,138,147,154],"difficulty":[25],"in":[26],"collecting":[27],"large":[28],"quantities":[29],"impaired":[31,63],"required":[33],"for":[34],"ASR":[35],"system":[36,126],"development.":[37],"This":[38],"paper":[39],"presents":[40],"novel":[41],"variational":[42],"auto-encoder":[43],"generative":[44],"adversarial":[45,97],"network":[46],"(VAE-GAN)":[47],"based":[48,129],"personalized":[49],"augmentation":[52,99,110,130],"approaches":[53],"that":[54],"simultaneously":[55],"learn":[56,71],"encode,":[58],"generate":[59],"and":[60,75,107,116,146],"discriminate":[61],"synthesized":[62],"speech.":[64],"Separate":[65],"latent":[66],"features":[67,84],"are":[68,85],"derived":[69],"dysarthric":[72,144],"characteristics":[74],"phoneme":[76],"context":[77],"representations.":[78],"Self-supervised":[79],"pre-trained":[80],"Wav2vec":[81],"2.0":[82],"embedding":[83],"also":[86],"incorporated.":[87],"Experiments":[88],"conducted":[89],"on":[90,137,153],"UASpeech":[92,139],"corpus":[93],"suggest":[94],"proposed":[96],"data":[98],"approach":[100],"consistently":[101],"outperformed":[102],"baseline":[104],"speed":[105],"perturbation":[106],"non-VAE":[108],"GAN":[109],"methods":[111],"trained":[113],"hybrid":[114],"TDNN":[115],"End-to-end":[117],"Conformer":[118],"systems.":[119],"After":[120],"LHUC":[121],"speaker":[122],"adaptation,":[123],"best":[125],"using":[127],"VAE-GAN":[128],"produced":[131],"an":[132],"overall":[133],"WER":[134,150],"27.78%":[136],"test":[140],"set":[141],"16":[143],"speakers,":[145],"lowest":[148],"published":[149],"57.31%":[152],"subset":[155],"speakers":[157],"\"Very":[159],"Low\"":[160],"intelligibility.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}