{"id":"https://openalex.org/W4297841594","doi":"https://doi.org/10.21437/interspeech.2022-10900","title":"Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification","display_name":"Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841594","doi":"https://doi.org/10.21437/interspeech.2022-10900"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10900","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10900","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/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"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":["Center for Language and Speech Processing,","Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence 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"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"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/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Vel\u00e1zquez","raw_affiliation_strings":["Center for Language and Speech Processing,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"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"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9714000225067139,"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/computer-science","display_name":"Computer science","score":0.8107219338417053},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7248542904853821},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.6588497161865234},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6415133476257324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5922924280166626},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5489679574966431},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5007760524749756},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4974105656147003},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4586058557033539},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.43048471212387085},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.24240437150001526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2376234233379364},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1430932879447937},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08829903602600098},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07073891162872314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0642489492893219},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05289706587791443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107219338417053},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7248542904853821},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.6588497161865234},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6415133476257324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5922924280166626},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5489679574966431},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5007760524749756},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4974105656147003},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4586058557033539},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.43048471212387085},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.24240437150001526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2376234233379364},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1430932879447937},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08829903602600098},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07073891162872314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0642489492893219},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05289706587791443},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10900","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10900","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1522301498","https://openalex.org/W1731081199","https://openalex.org/W2132462584","https://openalex.org/W2219249508","https://openalex.org/W2360384684","https://openalex.org/W2593414223","https://openalex.org/W2888908158","https://openalex.org/W2890964092","https://openalex.org/W2936028438","https://openalex.org/W2938553806","https://openalex.org/W2939878283","https://openalex.org/W2952218014","https://openalex.org/W2963057973","https://openalex.org/W2964117661","https://openalex.org/W2972961496","https://openalex.org/W2981087920","https://openalex.org/W2981885563","https://openalex.org/W2989863749","https://openalex.org/W3008883495","https://openalex.org/W3016143998","https://openalex.org/W3025227912","https://openalex.org/W3025443576","https://openalex.org/W3092028330","https://openalex.org/W3096324175","https://openalex.org/W3160652646","https://openalex.org/W3194763370","https://openalex.org/W3197934710","https://openalex.org/W4283014282","https://openalex.org/W4298289240"],"related_works":["https://openalex.org/W2059847929","https://openalex.org/W4319862422","https://openalex.org/W1971598839","https://openalex.org/W2765800144","https://openalex.org/W3144767625","https://openalex.org/W2017964352","https://openalex.org/W3207737697","https://openalex.org/W2097303478","https://openalex.org/W2006045908","https://openalex.org/W2023720074"],"abstract_inverted_index":{"Speech":[0],"systems":[1],"developed":[2,52],"for":[3,76,93,113],"a":[4,81,88,103,151,158],"particular":[5],"choice":[6],"of":[7,72],"acoustic":[8],"domain":[9,24,90],"and":[10,26,54,62,69,121,155],"sampling":[11],"frequency":[12],"do":[13],"not":[14],"translate":[15],"easily":[16],"to":[17,22,31,35,42,48],"others.The":[18],"usual":[19],"practice":[20],"is":[21,132],"learn":[23,36,41],"adaptation":[25,91],"bandwidth":[27,96,160],"extension":[28,97],"models":[29,75],"independently.Contrary":[30],"this,":[32],"we":[33,40,65,79,86],"propose":[34,80],"both":[37,60,130],"tasks":[38,131],"together.Particularly,":[39],"map":[43],"narrowband":[44],"conversational":[45],"telephone":[46],"speech":[47],"wideband":[49],"microphone":[50],"speech.We":[51],"parallel":[53],"non-parallel":[55],"learning":[56,83,129,135,153],"solutions":[57],"which":[58,116],"utilize":[59],"paired":[61],"unpaired":[63],"data.First,":[64],"first":[66,126],"discuss":[67],"joint":[68],"disjoint":[70],"training":[71],"multiple":[73],"generative":[74],"our":[77,100,139],"tasks.Then,":[78],"two-stage":[82],"solution":[84],"where":[85],"use":[87],"pre-trained":[89],"system":[92,141],"pre-processing":[94],"in":[95,146],"training.We":[98],"evaluated":[99],"schemes":[101],"on":[102],"Speaker":[104],"Verification":[105],"downstream":[106],"task.We":[107],"used":[108],"the":[109,125],"JHU-MIT":[110],"experimental":[111],"setup":[112],"NIST":[114],"SRE21,":[115],"comprises":[117],"SRE16,":[118,138],"SRE-CTS":[119],"Superset":[120],"SRE21.Our":[122],"results":[123],"provide":[124],"evidence":[127],"that":[128],"better":[133],"than":[134],"just":[136],"one.On":[137],"best":[140],"achieves":[142],"22%":[143],"relative":[144],"improvement":[145],"Equal":[147],"Error":[148],"Rate":[149],"w.r.t.":[150,157],"direct":[152],"baseline":[154],"8%":[156],"strong":[159],"expansion":[161],"system.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}