{"id":"https://openalex.org/W2936028438","doi":"https://doi.org/10.1109/icassp.2019.8683055","title":"Cycle-GANs for Domain Adaptation of Acoustic Features for Speaker Recognition","display_name":"Cycle-GANs for Domain Adaptation of Acoustic Features for Speaker Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936028438","doi":"https://doi.org/10.1109/icassp.2019.8683055","mag":"2936028438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5005758272","display_name":"Phani Sankar Nidadavolu","orcid":null},"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":"Phani Sankar Nidadavolu","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, 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":"Jesus Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, 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":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6206","last_page":"6210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.8315290212631226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7769179344177246},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6935306787490845},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.601187527179718},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.523655354976654},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5132126808166504},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5112357139587402},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5077551603317261},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5000653266906738},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4870167374610901},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4367430806159973},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41935741901397705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41198229789733887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4051496982574463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315290212631226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7769179344177246},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6935306787490845},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.601187527179718},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.523655354976654},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5132126808166504},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5112357139587402},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5077551603317261},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5000653266906738},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4870167374610901},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4367430806159973},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41935741901397705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41198229789733887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4051496982574463},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/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/icassp.2019.8683055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2099471712","https://openalex.org/W2173520492","https://openalex.org/W2294814385","https://openalex.org/W2344594423","https://openalex.org/W2516764878","https://openalex.org/W2553897675","https://openalex.org/W2593414223","https://openalex.org/W2726515241","https://openalex.org/W2774848319","https://openalex.org/W2787133659","https://openalex.org/W2796010067","https://openalex.org/W2888858245","https://openalex.org/W2890964092","https://openalex.org/W2962793481","https://openalex.org/W2963057973","https://openalex.org/W2963539064","https://openalex.org/W2963684088","https://openalex.org/W2964069186","https://openalex.org/W4293398859","https://openalex.org/W4320013936","https://openalex.org/W6631362777","https://openalex.org/W6685352114","https://openalex.org/W6730095352","https://openalex.org/W6746801104"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1977167953","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"It":[0],"is":[1],"well":[2],"known":[3],"that":[4],"domain":[5,25,70,100],"mismatch":[6,37],"between":[7,80,93],"the":[8,14,36],"training":[9],"and":[10,41,116,125],"evaluation":[11,53],"data":[12,54,92],"hinders":[13],"performance":[15],"of":[16],"any":[17,90],"machine":[18],"learning":[19,77],"system.":[20],"Various":[21],"factors":[22],"contribute":[23],"to":[24,35,98,103],"mismatch.":[26],"In":[27,58,65],"speaker":[28,44,105],"recognition":[29,45,106],"systems,":[30],"it":[31],"mainly":[32],"occurs":[33],"due":[34],"in":[38,120],"recording":[39],"conditions":[40],"language.":[42],"Most":[43],"corpora":[46],"are":[47,62,101],"telephone":[48,99,111],"speech.":[49,64],"Meanwhile,":[50],"a":[51],"few":[52],"sets":[55],"like":[56],"Speakers":[57],"The":[59],"Wild":[60],"(SITW)":[61],"microphone":[63],"this":[66],"work,":[67],"we":[68],"explore":[69],"adaptation":[71],"at":[72],"acoustic":[73],"feature":[74,78],"level":[75],"by":[76],"mappings":[79],"domains":[81],"using":[82],"cycle":[83],"consistent":[84],"generative":[85],"adversarial":[86],"networks":[87],"(cycle-GANs),":[88],"without":[89],"parallel":[91],"domains.":[94],"Microphone":[95],"features":[96],"mapped":[97],"used":[102],"evaluate":[104],"system":[107],"trained":[108],"only":[109],"on":[110,130],"data.":[112],"We":[113],"achieved":[114],"9.37%":[115],"2.82%":[117],"relative":[118],"improvement":[119],"equal":[121],"error":[122],"rate":[123],"(EER)":[124],"detection":[126],"cost":[127],"function":[128],"(DCF)":[129],"SITW":[131],"eval":[132],"set.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}