{"id":"https://openalex.org/W4392124226","doi":"https://doi.org/10.1109/taslp.2024.3369536","title":"Time-Domain Speech Super-Resolution With GAN Based Modeling for Telephony Speaker Verification","display_name":"Time-Domain Speech Super-Resolution With GAN Based Modeling for Telephony Speaker Verification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392124226","doi":"https://doi.org/10.1109/taslp.2024.3369536"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3369536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369536","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/A5014918159","display_name":"Saurabh Kataria","orcid":"https://orcid.org/0000-0001-6311-2155"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-6311-2155","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-9459-8426","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Vel\u00e1zquez","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-3033-7005","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","Meaning, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-8245-0413","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Meaning, Baltimore, MD, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-4489-5753","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.4077,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79708781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"1736","last_page":"1749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.6605285406112671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6157649755477905},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.5873246788978577},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5522036552429199},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45558083057403564},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43990689516067505},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2837209105491638},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09764471650123596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605285406112671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6157649755477905},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.5873246788978577},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5522036552429199},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45558083057403564},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43990689516067505},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2837209105491638},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09764471650123596},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3369536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369536","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W1517841224","https://openalex.org/W1522137499","https://openalex.org/W1552314771","https://openalex.org/W1586405805","https://openalex.org/W1994997782","https://openalex.org/W2069406404","https://openalex.org/W2125389028","https://openalex.org/W2131822572","https://openalex.org/W2141998673","https://openalex.org/W2167341025","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2290318471","https://openalex.org/W2399742709","https://openalex.org/W2404617565","https://openalex.org/W2515002297","https://openalex.org/W2516001803","https://openalex.org/W2518315489","https://openalex.org/W2566079294","https://openalex.org/W2593414223","https://openalex.org/W2801903454","https://openalex.org/W2888908158","https://openalex.org/W2890964092","https://openalex.org/W2938553806","https://openalex.org/W2939878283","https://openalex.org/W2940290905","https://openalex.org/W2944613371","https://openalex.org/W2950689937","https://openalex.org/W2952218014","https://openalex.org/W2962793481","https://openalex.org/W2972707556","https://openalex.org/W2972961496","https://openalex.org/W2973141395","https://openalex.org/W2973190269","https://openalex.org/W2981087920","https://openalex.org/W2982037672","https://openalex.org/W2989863749","https://openalex.org/W2998639482","https://openalex.org/W3015338123","https://openalex.org/W3024219829","https://openalex.org/W3024301174","https://openalex.org/W3025443576","https://openalex.org/W3095802501","https://openalex.org/W3096324175","https://openalex.org/W3096831136","https://openalex.org/W3099330747","https://openalex.org/W3137249133","https://openalex.org/W3160652646","https://openalex.org/W3161236344","https://openalex.org/W3163827866","https://openalex.org/W3174758275","https://openalex.org/W3197624376","https://openalex.org/W3197934710","https://openalex.org/W3204950929","https://openalex.org/W3211264909","https://openalex.org/W3217778739","https://openalex.org/W4214701208","https://openalex.org/W4221155904","https://openalex.org/W4283010431","https://openalex.org/W4283067253","https://openalex.org/W4283078310","https://openalex.org/W4285412734","https://openalex.org/W4296069276","https://openalex.org/W4297841594","https://openalex.org/W4297841898","https://openalex.org/W6631190155","https://openalex.org/W6678815747","https://openalex.org/W6688816777","https://openalex.org/W6713727690","https://openalex.org/W6735913928","https://openalex.org/W6741832134","https://openalex.org/W6767111847","https://openalex.org/W6779841522","https://openalex.org/W6783867762","https://openalex.org/W6785984853","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Automatic":[0],"Speaker":[1],"Verification(ASV)":[2],"technology":[3],"has":[4],"become":[5],"commonplace":[6],"in":[7,178,194],"virtual":[8],"assistants.":[9],"However,":[10],"its":[11],"performance":[12],"suffers":[13],"when":[14],"there":[15],"is":[16,35],"a":[17,36,41,111,221,231],"mismatch":[18],"between":[19],"the":[20,114,179,195,199],"train":[21],"and":[22,49,73,102,131,157,168,172,185,206,240],"test":[23,151],"domains.":[24,51],"Mixed":[25],"bandwidth":[26,67,129,214],"training,":[27],"i.e.,":[28],"pooling":[29],"training":[30,115,155],"data":[31,121],"from":[32],"both":[33,47],"domains,":[34],"preferred":[37],"choice":[38],"for":[39,46,98],"developing":[40],"universal":[42],"model":[43],"that":[44,212],"works":[45],"narrowband":[48,62],"wideband":[50,228],"We":[52,69,90,135,163,210],"propose":[53],"complementing":[54],"this":[55],"technique":[56],"by":[57,139],"performing":[58],"neural":[59],"upsampling":[60],"of":[61,116,183,198,223,234],"signals,":[63,230],"also":[64],"known":[65],"as":[66,110,220],"extension.":[68],"aim":[70],"to":[71,83,217],"discover":[72],"analyze":[74],"high-performing":[75],"time-domain":[76,142],"Generative":[77],"Adversarial":[78],"Network":[79],"(GAN)":[80],"based":[81],"models":[82],"improve":[84],"our":[85,213],"downstream":[86,117,238],"state-of-the-art":[87],"ASV":[88,207],"system.":[89],"choose":[91],"GANs":[92,170],"since":[93],"they":[94],"1)":[95,140],"are":[96],"powerful":[97],"learning":[99],"conditional":[100],"distribution":[101],"2)":[103,145],"allow":[104],"flexible":[105],"<italic":[106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">plug-in</i>":[108],"usage":[109],"pre-processor":[112],"during":[113],"tasks":[118],"(ASV)":[119],"with":[120,237],"augmentation.":[122],"Prior":[123],"work":[124],"mainly":[125],"focused":[126],"on":[127,148],"feature-domain":[128],"extension":[130,143,215],"limited":[132],"experimental":[133],"setups.":[134],"address":[136],"these":[137],"limitations":[138],"using":[141],"models,":[144],"reporting":[146],"results":[147],"three":[149],"real":[150],"sets,":[152],"3)":[153],"extending":[154],"data,":[156],"4)":[158],"devising":[159],"new":[160],"test-time":[161],"schemes.":[162],"compare":[164],"supervised":[165],"(conditional":[166],"GAN)":[167],"unsupervised":[169],"(CycleGAN)":[171],"demonstrate":[173],"an":[174],"average":[175],"relative":[176],"improvement":[177],"equal":[180],"error":[181],"rate":[182],"8.6%":[184],"7.7%,":[186],"respectively.":[187],"For":[188],"further":[189],"analysis,":[190],"we":[191],"study":[192],"changes":[193],"visual":[196],"quality":[197,236],"spectrogram,":[200],"audio":[201],"perceptual":[202,235],"quality,":[203],"t-SNE":[204],"embeddings,":[205],"score":[208,242],"distributions.":[209],"show":[211],"leads":[216],"phenomena":[218],"such":[219],"shift":[222],"telephone":[224],"(test)":[225],"embeddings":[226],"towards":[227],"(train)":[229],"negative":[232],"correlation":[233],"performance,":[239],"condition-independent":[241],"calibration.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}