{"id":"https://openalex.org/W2938486422","doi":"https://doi.org/10.1109/icassp.2019.8683486","title":"Attentive Adversarial Learning for Domain-invariant Training","display_name":"Attentive Adversarial Learning for Domain-invariant Training","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938486422","doi":"https://doi.org/10.1109/icassp.2019.8683486","mag":"2938486422"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683486","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/1904.12400","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":1.302,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85318012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6740","last_page":"6744"},"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":0.9972000122070312,"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":0.9954000115394592,"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":0.9159723520278931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7308271527290344},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7123269438743591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6340528726577759},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.620042085647583},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5623725056648254},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5576316714286804},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5107951164245605},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5005905628204346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4974513351917267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4598759710788727},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.41192060708999634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3754631280899048},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11860883235931396},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09846916794776917}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9159723520278931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308271527290344},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7123269438743591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6340528726577759},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.620042085647583},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5623725056648254},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5576316714286804},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5107951164245605},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5005905628204346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4974513351917267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4598759710788727},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.41192060708999634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3754631280899048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11860883235931396},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09846916794776917},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683486","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:1904.12400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12400","pdf_url":"https://arxiv.org/pdf/1904.12400","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:1904.12400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12400","pdf_url":"https://arxiv.org/pdf/1904.12400","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":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1882958252","https://openalex.org/W1902237438","https://openalex.org/W1992475611","https://openalex.org/W2013598660","https://openalex.org/W2099471712","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2173520492","https://openalex.org/W2289394825","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2394932179","https://openalex.org/W2402040300","https://openalex.org/W2510867321","https://openalex.org/W2511131004","https://openalex.org/W2584667682","https://openalex.org/W2608338293","https://openalex.org/W2636483419","https://openalex.org/W2666408839","https://openalex.org/W2735006420","https://openalex.org/W2769025471","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2802023636","https://openalex.org/W2804078698","https://openalex.org/W2885706078","https://openalex.org/W2888858245","https://openalex.org/W2889500840","https://openalex.org/W2907262790","https://openalex.org/W2936252403","https://openalex.org/W2937328535","https://openalex.org/W2939164678","https://openalex.org/W2953127297","https://openalex.org/W2962684181","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963266252","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963684088","https://openalex.org/W2963826681","https://openalex.org/W3112742522","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6639480849","https://openalex.org/W6653897473","https://openalex.org/W6685352114","https://openalex.org/W6711962127","https://openalex.org/W6712847557","https://openalex.org/W6725448924","https://openalex.org/W6732862412","https://openalex.org/W6735429107","https://openalex.org/W6739901393","https://openalex.org/W6745924425","https://openalex.org/W6752378368","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W4321441197","https://openalex.org/W2995777218","https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W4383221314","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W3203790781","https://openalex.org/W4313346231","https://openalex.org/W2738001131"],"abstract_inverted_index":{"Adversarial":[0],"domain-invariant":[1],"training":[2],"(ADIT)":[3],"proves":[4],"to":[5,21,51,81,89,113,138,154],"be":[6,152],"effective":[7],"in":[8,15,24,36,70,92,147],"suppressing":[9],"the":[10,74,84,103,129,139,156,165,182],"effects":[11],"of":[12,106],"domain":[13,33,75,93,104,114],"variability":[14,115],"acoustic":[16,46,141,157],"modeling":[17,158],"and":[18,48,116,123,143,186,196],"has":[19],"led":[20],"improved":[22,121],"performance":[23],"automatic":[25],"speech":[26],"recognition":[27],"(ASR).":[28],"In":[29,61],"ADIT,":[30],"an":[31,57,66,78,135,175],"auxiliary":[32,176],"classifier":[34,76],"takes":[35],"equally-weighted":[37],"deep":[38,42,86,118],"features":[39,87,119],"from":[40],"a":[41,193,197],"neural":[43],"network":[44],"(DNN)":[45],"model":[47,142,195],"is":[49,144],"trained":[50],"improve":[52,155,169],"their":[53,90],"domain-invariance":[54,122],"by":[55],"optimizing":[56],"adversarial":[58,171],"loss":[59],"function.":[60],"this":[62,96],"work,":[63],"we":[64,72],"propose":[65],"attentive":[67,97],"ADIT":[68,199],"(AADIT)":[69],"which":[71],"advance":[73],"with":[77,120,159,174],"attention":[79,130],"mechanism":[80],"automatically":[82],"weight":[83],"input":[85],"according":[88],"importance":[91],"classification.":[94],"With":[95],"re-weighting,":[98],"ADDIT":[99],"can":[100,151,168],"focus":[101],"on":[102,179],"normalization":[105],"phonetic":[107],"components":[108],"that":[109],"are":[110],"more":[111],"susceptible":[112],"generates":[117],"senone-discriminativity":[124],"over":[125,192],"ADIT.":[126],"Most":[127],"importantly,":[128],"block":[131],"serves":[132],"only":[133],"as":[134],"external":[136],"component":[137],"DNN":[140,161],"not":[145],"involved":[146],"ASR,":[148],"so":[149],"AADIT":[150,183],"used":[153],"any":[160,170],"architectures.":[162],"More":[163],"generally,":[164],"same":[166],"methodology":[167],"learning":[172],"system":[173],"discriminator.":[177],"Evaluated":[178],"CHiME-3":[180],"dataset,":[181],"achieves":[184],"13.6%":[185],"9.3%":[187],"relative":[188],"WER":[189],"improvements,":[190],"respectively,":[191],"multi-conditional":[194],"strong":[198],"baseline.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}