{"id":"https://openalex.org/W2939164678","doi":"https://doi.org/10.1109/icassp.2019.8682510","title":"Adversarial Speaker Adaptation","display_name":"Adversarial Speaker Adaptation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939164678","doi":"https://doi.org/10.1109/icassp.2019.8682510","mag":"2939164678"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682510","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.12407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.3399,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9544914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5721","last_page":"5725"},"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":0.9991999864578247,"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":0.9966999888420105,"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/discriminator","display_name":"Discriminator","score":0.8252453804016113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830402255058289},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7486119270324707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7409673929214478},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5967599749565125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919236540794373},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5320514440536499},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.525503396987915},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5249800086021423},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4912533164024353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48842301964759827},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4515475630760193},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4369986057281494},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4221551716327667},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.410690039396286},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27579265832901}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8252453804016113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830402255058289},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7486119270324707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7409673929214478},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5967599749565125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919236540794373},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5320514440536499},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.525503396987915},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5249800086021423},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4912533164024353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48842301964759827},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4515475630760193},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4369986057281494},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4221551716327667},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.410690039396286},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27579265832901},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682510","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"},{"id":"pmh:oai:arXiv.org:1904.12407","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12407","pdf_url":"https://arxiv.org/pdf/1904.12407","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.12407","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12407","pdf_url":"https://arxiv.org/pdf/1904.12407","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","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1513862252","https://openalex.org/W1882958252","https://openalex.org/W1965555277","https://openalex.org/W1989549063","https://openalex.org/W1992475611","https://openalex.org/W1993409002","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2099471712","https://openalex.org/W2112021726","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2294543795","https://openalex.org/W2307663696","https://openalex.org/W2394882406","https://openalex.org/W2407793339","https://openalex.org/W2510867321","https://openalex.org/W2511131004","https://openalex.org/W2584667682","https://openalex.org/W2587088898","https://openalex.org/W2636483419","https://openalex.org/W2735006420","https://openalex.org/W2769025471","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2801581493","https://openalex.org/W2829750449","https://openalex.org/W2888858245","https://openalex.org/W2889500840","https://openalex.org/W2894728377","https://openalex.org/W2936252403","https://openalex.org/W2937328535","https://openalex.org/W2938486422","https://openalex.org/W2963266252","https://openalex.org/W2963288281","https://openalex.org/W2963341071","https://openalex.org/W2963826681","https://openalex.org/W2964182776","https://openalex.org/W3106526813","https://openalex.org/W3112742522","https://openalex.org/W4320013936","https://openalex.org/W6639480849","https://openalex.org/W6639822467","https://openalex.org/W6676587989","https://openalex.org/W6696912008","https://openalex.org/W6713823255","https://openalex.org/W6732862412","https://openalex.org/W6735429107","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W2574073913","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W2008737763","https://openalex.org/W4385611764"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,24,39,74,111,122,133],"novel":[3],"adversarial":[4,11],"speaker":[5],"adaptation":[6,107,188],"(ASA)":[7],"scheme,":[8],"in":[9,23,117],"which":[10],"learning":[12],"is":[13,52,84,115],"applied":[14],"to":[15,33,36,54,91,99,125],"regularize":[16],"the":[17,56,61,68,79,88,93,101,106,118,128,139,149,155],"distribution":[18,124],"of":[19,38,127],"deep":[20,27,57,113,137],"hidden":[21],"features":[22,58],"speaker-dependent":[25],"(SD)":[26],"neural":[28],"network":[29,51,90],"(DNN)":[30],"acoustic":[31,44],"model":[32,45,63,77,83,120,141,180],"be":[34],"close":[35],"that":[37,126],"fixed":[40,75],"speaker-independent":[41],"(SI)":[42],"DNN":[43],"during":[46],"adaptation.":[47],"An":[48],"additional":[49],"discriminator":[50,89],"introduced":[53],"distinguish":[55],"generated":[59],"by":[60,67],"SD":[62,82,119,140],"from":[64,182],"those":[65],"produced":[66],"SI":[69,76,129,179],"model.":[70,130],"In":[71],"ASA,":[72,110],"with":[73,87,121,186],"as":[78],"reference,":[80],"an":[81,178],"jointly":[85],"optimized":[86],"minimize":[92],"senone":[94],"classification":[95],"loss,":[96],"and":[97,135,164,173],"simultaneously":[98],"mini-maximize":[100],"SI/SD":[102],"discrimination":[103],"loss":[104],"on":[105,148,154],"data.":[108],"With":[109,131],"senone-discriminative":[112],"feature":[114],"learned":[116],"similar":[123],"such":[132],"regularized":[134],"adapted":[136],"feature,":[138],"can":[142],"perform":[143],"improved":[144],"automatic":[145],"speech":[146],"recognition":[147],"target":[150],"speaker's":[151],"speech.":[152],"Evaluated":[153],"Microsoft":[156],"short":[157],"message":[158],"dictation":[159],"dataset,":[160],"ASA":[161],"achieves":[162],"14.4%":[163],"7.9%":[165],"relative":[166],"word":[167],"error":[168],"rate":[169],"improvements":[170],"for":[171],"supervised":[172],"unsupervised":[174],"adaptation,":[175],"respectively,":[176],"over":[177],"trained":[181],"2600":[183],"hours":[184],"data,":[185],"200":[187],"utterances":[189],"per":[190],"speaker.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}