{"id":"https://openalex.org/W3150852537","doi":"https://doi.org/10.21437/interspeech.2021-1502","title":"Deep Feature CycleGANs: Speaker Identity Preserving Non-Parallel Microphone-Telephone Domain Adaptation for Speaker Verification","display_name":"Deep Feature CycleGANs: Speaker Identity Preserving Non-Parallel Microphone-Telephone Domain Adaptation for Speaker Verification","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3150852537","doi":"https://doi.org/10.21437/interspeech.2021-1502","mag":"3150852537"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1502","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.01433","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014918159","display_name":"Saurabh Kataria","orcid":"https://orcid.org/0000-0001-6311-2155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laureano Moro-Vel\u00e1zquez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1079","last_page":"1083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7887294292449951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7188427448272705},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6554883122444153},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.5343757271766663},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4865533411502838},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4848981499671936},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4507911801338196},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4278271496295929},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4157925248146057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3950888216495514},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1068609356880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887294292449951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7188427448272705},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6554883122444153},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.5343757271766663},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4865533411502838},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4848981499671936},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4507911801338196},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4278271496295929},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4157925248146057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3950888216495514},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1068609356880188},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1502","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.01433","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01433","pdf_url":"https://arxiv.org/pdf/2104.01433","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2104.01433","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.01433","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3150852537","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01433","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01433","pdf_url":"https://arxiv.org/pdf/2104.01433","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3150852537.pdf","grobid_xml":"https://content.openalex.org/works/W3150852537.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1710476689","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2593414223","https://openalex.org/W2726515241","https://openalex.org/W2774848319","https://openalex.org/W2780407133","https://openalex.org/W2786672974","https://openalex.org/W2798729263","https://openalex.org/W2890964092","https://openalex.org/W2914282508","https://openalex.org/W2935938411","https://openalex.org/W2936028438","https://openalex.org/W2962793481","https://openalex.org/W2965095304","https://openalex.org/W2968378480","https://openalex.org/W2970006822","https://openalex.org/W2972443522","https://openalex.org/W2973000846","https://openalex.org/W2982037672","https://openalex.org/W3008883495","https://openalex.org/W3016143998","https://openalex.org/W3024219829","https://openalex.org/W3024301174","https://openalex.org/W3025227912","https://openalex.org/W3025443576","https://openalex.org/W3027343259","https://openalex.org/W3103152812","https://openalex.org/W3110137169","https://openalex.org/W3129296553","https://openalex.org/W3138129477","https://openalex.org/W3152148971","https://openalex.org/W3163827866"],"related_works":["https://openalex.org/W3197934710","https://openalex.org/W3008883495","https://openalex.org/W3163829335","https://openalex.org/W2936028438","https://openalex.org/W3014794275","https://openalex.org/W3016048045","https://openalex.org/W3012170331","https://openalex.org/W3163929126","https://openalex.org/W3211614993","https://openalex.org/W2790216641","https://openalex.org/W3201363892","https://openalex.org/W3012043827","https://openalex.org/W2935938411","https://openalex.org/W3005914302","https://openalex.org/W2339276216","https://openalex.org/W3097470351","https://openalex.org/W3011028252","https://openalex.org/W1585307611","https://openalex.org/W3015678936","https://openalex.org/W3198543387"],"abstract_inverted_index":{"With":[0],"the":[1,4,41,55,66,81,86,102,166],"increase":[2],"in":[3,101,136],"availability":[5],"of":[6,50,68,108,134,138,150,168,177],"speech":[7,22,39],"from":[8,113],"varied":[9],"domains,":[10],"it":[11,35],"is":[12,26],"imperative":[13],"to":[14,19,40,53,76,84,99],"use":[15],"such":[16],"out-of-domain":[17],"data":[18,52,73,156,158],"improve":[20,54,77],"existing":[21],"systems.":[23],"Domain":[24],"adaptation":[25,87],"a":[27,109,147,173],"prominent":[28],"pre-processing":[29],"approach":[30],"for":[31,36,59],"this.":[32],"We":[33,63,89],"investigate":[34],"adapt":[37],"microphone":[38,51,153],"telephone":[42,155,161],"domain.":[43],"Specifically,":[44],"we":[45,79,145,164],"explore":[46],"CycleGAN-based":[47],"unpaired":[48],"translation":[49],"x-vector/speaker":[56],"embedding":[57],"network":[58,118],"Telephony":[60],"Speaker":[61],"Verification.":[62],"first":[64],"demonstrate":[65],"efficacy":[67],"this":[69],"on":[70],"real":[71],"challenging":[72,148],"and":[74,96,154,160,171],"then,":[75],"further,":[78],"modify":[80,90],"CycleGAN":[82,169],"formulation":[83],"make":[85],"task-specific.":[88],"CycleGAN's":[91],"identity":[92],"loss,":[93,95],"cycle-consistency":[94],"adversarial":[97],"loss":[98],"operate":[100],"deep":[103],"feature":[104],"space.":[105],"Deep":[106,127],"features":[107],"signal":[110],"are":[111],"extracted":[112],"an":[114],"auxiliary":[115],"(speaker":[116],"embedding)":[117],"and,":[119],"hence,":[120],"preserves":[121],"speaker":[122],"identity.":[123],"Our":[124],"3D":[125],"convolution-based":[126],"Feature":[128],"Discriminators":[129],"(DFD)":[130],"show":[131],"relative":[132],"improvements":[133],"5-10%":[135],"terms":[137],"equal":[139],"error":[140],"rate.":[141],"To":[142],"dive":[143],"deeper,":[144],"study":[146],"scenario":[149],"pooling":[151],"(adapted)":[152],"with":[157],"augmentations":[159],"codecs.":[162],"Finally,":[163],"highlight":[165],"sensitivity":[167],"hyper-parameters":[170],"introduce":[172],"parameter":[174],"called":[175],"probability":[176],"adaptation.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}