{"id":"https://openalex.org/W4225289116","doi":"https://doi.org/10.1109/icassp43922.2022.9746680","title":"Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation","display_name":"Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225289116","doi":"https://doi.org/10.1109/icassp43922.2022.9746680"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746680","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Disong Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037078872","display_name":"Hui Jing Lu","orcid":"https://orcid.org/0000-0003-4025-3160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019219958","display_name":"Lifa Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifa Sun","raw_affiliation_strings":["SpeechX Limited,Shenzhen,China","SpeechX Limited, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"SpeechX Limited,Shenzhen,China","institution_ids":[]},{"raw_affiliation_string":"SpeechX Limited, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","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":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China","Centre for Perceptual and Interactive Intelligence, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068726270"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.0388,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77731092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6677","last_page":"6681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9987000226974487,"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":0.8019285798072815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7159523963928223},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.61119544506073},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5733259320259094},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5251243710517883},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.48543936014175415},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.46399280428886414},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4517768919467926},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.429210901260376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4252215325832367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3865737020969391},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13377892971038818},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08873987197875977}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8019285798072815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159523963928223},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.61119544506073},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5733259320259094},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5251243710517883},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.48543936014175415},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46399280428886414},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4517768919467926},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.429210901260376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4252215325832367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3865737020969391},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13377892971038818},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08873987197875977},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746680","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W180052447","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1540882196","https://openalex.org/W1999799863","https://openalex.org/W2005768155","https://openalex.org/W2011378162","https://openalex.org/W2022125261","https://openalex.org/W2077801020","https://openalex.org/W2078722660","https://openalex.org/W2124641009","https://openalex.org/W2142300631","https://openalex.org/W2527729766","https://openalex.org/W2545886659","https://openalex.org/W2547364378","https://openalex.org/W2576309025","https://openalex.org/W2726515241","https://openalex.org/W2747874407","https://openalex.org/W2748881396","https://openalex.org/W2808631503","https://openalex.org/W2902967674","https://openalex.org/W2939164678","https://openalex.org/W2962788625","https://openalex.org/W2963767194","https://openalex.org/W2972970915","https://openalex.org/W2973053330","https://openalex.org/W2973215447","https://openalex.org/W3015338123","https://openalex.org/W3015430779","https://openalex.org/W3015707856","https://openalex.org/W3097881066","https://openalex.org/W3161018648","https://openalex.org/W3194248215","https://openalex.org/W3196305160","https://openalex.org/W3198218550","https://openalex.org/W6600284362","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6632513598","https://openalex.org/W6727697161","https://openalex.org/W6729138736","https://openalex.org/W6745415975","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,24,102,138,146,163,176],"reconstruction":[2],"(DSR),":[3],"which":[4],"aims":[5],"to":[6,21,25,51,63,108,120,139,142],"improve":[7],"the":[8,23,32,40,53,57,66,98,101,104,114,122,129,134,153,174],"quality":[9],"of":[10,68,95,103,124,136,144],"dysarthric":[11,69,106,172],"speech,":[12,131,173],"remains":[13],"a":[14,82,166],"challenge,":[15],"not":[16,60],"only":[17],"because":[18],"we":[19,80],"need":[20],"restore":[22],"be":[26,61,140],"normal,":[27],"but":[28],"also":[29],"must":[30],"preserve":[31],"speaker\u2019s":[33],"identity.":[34,55],"The":[35,92],"speaker":[36,41,46,54,89,107,159],"representation":[37],"extracted":[38],"by":[39,132],"encoder":[42],"(SE)":[43],"optimized":[44],"for":[45,186],"verification":[47],"has":[48],"been":[49],"explored":[50],"control":[52],"However,":[56],"SE":[58,99],"may":[59],"able":[62],"fully":[64],"capture":[65,110],"characteristics":[67],"speakers":[70,187],"that":[71,143,152],"are":[72],"previously":[73],"unseen.":[74],"To":[75],"address":[76],"this":[77],"research":[78],"problem,":[79],"propose":[81],"novel":[83],"multi-task":[84],"learning":[85],"strategy,":[86],"i.e.,":[87],"adversarial":[88,118],"adaptation":[90],"(ASA).":[91],"primary":[93],"task":[94,116],"ASA":[96],"fine-tunes":[97],"with":[100,147,165,171,188],"target":[105],"effectively":[109],"identityrelated":[111],"information,":[112],"and":[113,161,179,190],"secondary":[115],"applies":[117],"training":[119],"avoid":[121],"incorporation":[123],"abnormal":[125],"speaking":[126],"patterns":[127],"into":[128],"reconstructed":[130,137,175],"regularizing":[133],"distribution":[135],"close":[141],"reference":[145],"high":[148],"quality.":[149],"Experiments":[150],"show":[151],"proposed":[154],"approach":[155],"can":[156],"achieve":[157],"enhanced":[158],"similarity":[160],"comparable":[162],"naturalness":[164],"strong":[167],"baseline":[168],"approach.":[169],"Compared":[170],"achieves":[177],"22.3%":[178],"31.5%":[180],"absolute":[181],"word":[182],"error":[183],"rate":[184],"reduction":[185],"moderate":[189],"moderate-severe":[191],"dysarthria":[192],"respectively.":[193],"Our":[194],"demo":[195],"page":[196],"is":[197],"released":[198],"here":[199],"<sup":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[202],".":[203]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
