{"id":"https://openalex.org/W4387682382","doi":"https://doi.org/10.1109/taslp.2023.3323888","title":"Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition","display_name":"Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4387682382","doi":"https://doi.org/10.1109/taslp.2023.3323888"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3323888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3323888","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2637-7880","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7886-439X","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, 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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8874-4167","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, 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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0005-5823-3039","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, 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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8475-4912","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, 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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2206-0237","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, 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":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6725-1160","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":6.0278,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96959898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"413","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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":0.9972000122070312,"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":0.996399998664856,"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/T10860","display_name":"Speech and Audio Processing","score":0.9914000034332275,"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":0.7443390488624573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7196499705314636},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4584819972515106},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.44589778780937195},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.445454865694046},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43360036611557007},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.41615837812423706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.343636155128479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31502971053123474},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08363142609596252}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7443390488624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196499705314636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4584819972515106},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.44589778780937195},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.445454865694046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43360036611557007},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.41615837812423706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.343636155128479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31502971053123474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08363142609596252},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3323888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3323888","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":135,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1494198834","https://openalex.org/W1631260214","https://openalex.org/W1853705225","https://openalex.org/W1877570817","https://openalex.org/W1902027874","https://openalex.org/W1932968309","https://openalex.org/W1979651826","https://openalex.org/W1989674786","https://openalex.org/W2014498736","https://openalex.org/W2018363392","https://openalex.org/W2020997493","https://openalex.org/W2036328773","https://openalex.org/W2039844283","https://openalex.org/W2045697402","https://openalex.org/W2047309943","https://openalex.org/W2074037951","https://openalex.org/W2085313529","https://openalex.org/W2109848220","https://openalex.org/W2130739159","https://openalex.org/W2137373451","https://openalex.org/W2139331960","https://openalex.org/W2140360678","https://openalex.org/W2143612262","https://openalex.org/W2148344853","https://openalex.org/W2166637769","https://openalex.org/W2168510624","https://openalex.org/W2171360373","https://openalex.org/W2239847623","https://openalex.org/W2250686550","https://openalex.org/W2327501763","https://openalex.org/W2396944218","https://openalex.org/W2398169716","https://openalex.org/W2401277329","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2510062933","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2749128330","https://openalex.org/W2752287204","https://openalex.org/W2770604845","https://openalex.org/W2790414498","https://openalex.org/W2792759062","https://openalex.org/W2806825704","https://openalex.org/W2883586237","https://openalex.org/W2888789389","https://openalex.org/W2888807255","https://openalex.org/W2889469831","https://openalex.org/W2891138528","https://openalex.org/W2936028438","https://openalex.org/W2936774411","https://openalex.org/W2936861580","https://openalex.org/W2937579788","https://openalex.org/W2944394478","https://openalex.org/W2944613371","https://openalex.org/W2962780374","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2963865582","https://openalex.org/W2964525587","https://openalex.org/W2969430620","https://openalex.org/W2972413216","https://openalex.org/W2972640480","https://openalex.org/W2972689158","https://openalex.org/W2972702443","https://openalex.org/W2972724712","https://openalex.org/W2973130159","https://openalex.org/W2973213659","https://openalex.org/W2981857663","https://openalex.org/W3007146018","https://openalex.org/W3008911072","https://openalex.org/W3011640397","https://openalex.org/W3012461590","https://openalex.org/W3014690389","https://openalex.org/W3015210890","https://openalex.org/W3015249983","https://openalex.org/W3015342653","https://openalex.org/W3015411705","https://openalex.org/W3015440307","https://openalex.org/W3015693260","https://openalex.org/W3015959238","https://openalex.org/W3016258016","https://openalex.org/W3034924009","https://openalex.org/W3049278490","https://openalex.org/W3095123370","https://openalex.org/W3096806728","https://openalex.org/W3097109903","https://openalex.org/W3097341038","https://openalex.org/W3097777922","https://openalex.org/W3097866346","https://openalex.org/W3097890746","https://openalex.org/W3097909406","https://openalex.org/W3097912232","https://openalex.org/W3110715635","https://openalex.org/W3125118953","https://openalex.org/W3134043075","https://openalex.org/W3140745443","https://openalex.org/W3157063407","https://openalex.org/W3161294170","https://openalex.org/W3161873458","https://openalex.org/W3163725792","https://openalex.org/W3163888473","https://openalex.org/W3174329270","https://openalex.org/W3196511136","https://openalex.org/W3197150384","https://openalex.org/W3197516274","https://openalex.org/W3197646400","https://openalex.org/W3197712601","https://openalex.org/W3197912841","https://openalex.org/W3197934710","https://openalex.org/W3197943112","https://openalex.org/W3198116506","https://openalex.org/W3198234802","https://openalex.org/W3198454118","https://openalex.org/W3198806843","https://openalex.org/W3207244775","https://openalex.org/W3207399576","https://openalex.org/W4200483526","https://openalex.org/W4206030489","https://openalex.org/W4221148457","https://openalex.org/W4221156109","https://openalex.org/W4221167580","https://openalex.org/W4224931267","https://openalex.org/W4225289116","https://openalex.org/W4225753921","https://openalex.org/W4254312214","https://openalex.org/W6603616073","https://openalex.org/W6631362777","https://openalex.org/W6675409298","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6727380140","https://openalex.org/W6729482032","https://openalex.org/W6776960109"],"related_works":["https://openalex.org/W1834994814","https://openalex.org/W2981428355","https://openalex.org/W1599055764","https://openalex.org/W2041273198","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Despite":[0],"the":[1,43,70,142,164,169,186,194,214,233],"rapid":[2],"progress":[3],"of":[4,15,34,76,94,127,155],"automatic":[5],"speech":[6,19,87,118,133,146,192,203],"recognition":[7,14],"(ASR)":[8],"technologies":[9],"targeting":[10],"normal":[11,86,117,145],"speech,":[12],"accurate":[13],"dysarthric":[16,191],"and":[17,85,123,137,175,189,198,223,227,235],"elderly":[18,84,158,202],"remains":[20],"a":[21,58,91,156],"highly":[22],"challenging":[23],"task":[24],"to":[25,30,42,63,120,125,150,167,221],"date.":[26],"It":[27],"is":[28,135],"difficult":[29],"collect":[31],"large":[32],"quantities":[33],"such":[35],"data":[36,54,65,102,134,171,209,237],"for":[37,139,172],"ASR":[38,177],"system":[39,178],"development":[40],"due":[41],"mobility":[44],"issues":[45],"often":[46],"found":[47],"among":[48],"these":[49],"users.":[50],"To":[51],"this":[52,106],"end,":[53],"augmentation":[55,66,103,210],"techniques":[56,67],"play":[57],"vital":[59],"role.":[60],"In":[61],"contrast":[62],"existing":[64],"only":[68],"modifying":[69],"speaking":[71],"rate":[72],"or":[73,114],"overall":[74],"shape":[75],"spectral":[77,147],"contour,":[78],"fine-grained":[79],"spectro-temporal":[80],"differences":[81],"between":[82],"dysarthric,":[83],"are":[88,181,242],"modelled":[89],"using":[90],"novel":[92],"set":[93],"speaker-dependent":[95],"(SD)":[96],"generative":[97],"adversarial":[98],"networks":[99],"(GAN)":[100],"based":[101,208,247],"approaches":[104,211],"in":[105],"article.":[107],"These":[108],"flexibly":[109],"allow":[110],"both:":[111],"a)":[112],"temporal":[113,165],"speed":[115,216],"perturbed":[116],"spectra":[119],"be":[121,151],"modified":[122],"closer":[124],"those":[126,154],"an":[128],"impaired":[129],"speaker":[130,159,248],"when":[131],"parallel":[132],"available;":[136],"b)":[138],"non-parallel":[140],"data,":[141],"SVD":[143],"decomposed":[144],"basis":[148],"features":[149],"transformed":[152],"into":[153],"target":[157],"before":[160],"being":[161],"re-composed":[162],"with":[163],"bases":[166],"produce":[168],"augmented":[170],"state-of-the-art":[173],"TDNN":[174],"Conformer":[176],"training.":[179],"Experiments":[180],"conducted":[182],"on":[183,232],"four":[184],"tasks:":[185],"English":[187,195],"UASpeech":[188],"TORGO":[190,234],"corpora;":[193],"DementiaBank":[196,236],"Pitt":[197],"Cantonese":[199],"JCCOCC":[200],"MoCA":[201],"datasets.":[204],"The":[205],"proposed":[206],"GAN":[207],"consistently":[212],"outperform":[213],"baseline":[215],"perturbation":[217],"method":[218],"by":[219],"up":[220],"0.91%":[222],"3.0%":[224],"absolute":[225],"(9.61%":[226],"6.4%":[228],"relative)":[229],"WER":[230],"reduction":[231],"respectively.":[238],"Consistent":[239],"performance":[240],"improvements":[241],"retained":[243],"after":[244],"applying":[245],"LHUC":[246],"adaptation.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
