{"id":"https://openalex.org/W2796339975","doi":"https://doi.org/10.1109/icassp.2018.8461932","title":"Speaker-Invariant Training Via Adversarial Learning","display_name":"Speaker-Invariant Training Via Adversarial Learning","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2796339975","doi":"https://doi.org/10.1109/icassp.2018.8461932","mag":"2796339975"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.00732","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/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"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 AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"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":"Zhuo Chen","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992618","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-1028-3406"},"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":"Yang Zhao","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042972227","display_name":"Vadim Mazalov","orcid":null},"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":"Vadim Mazalov","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928536","display_name":"Yifan Gong","orcid":null},"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 AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5087,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.98332205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5969","last_page":"5973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.998199999332428,"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/discriminative-model","display_name":"Discriminative model","score":0.789177417755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562294006347656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7496931552886963},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6255303621292114},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5970646739006042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5218081474304199},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5168126821517944},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4918051064014435},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.47295424342155457},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4425423741340637},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.44161564111709595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.410385400056839},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09573385119438171}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.789177417755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562294006347656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7496931552886963},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6255303621292114},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5970646739006042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5218081474304199},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5168126821517944},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4918051064014435},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47295424342155457},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4425423741340637},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.44161564111709595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.410385400056839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09573385119438171},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.00732","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00732","pdf_url":"https://arxiv.org/pdf/1804.00732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:1804.00732","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00732","pdf_url":"https://arxiv.org/pdf/1804.00732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1427982033","https://openalex.org/W1567690964","https://openalex.org/W1599512239","https://openalex.org/W1882958252","https://openalex.org/W1899458394","https://openalex.org/W1909308924","https://openalex.org/W2002342963","https://openalex.org/W2013598660","https://openalex.org/W2048526313","https://openalex.org/W2056738732","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2099471712","https://openalex.org/W2112021726","https://openalex.org/W2160815625","https://openalex.org/W2167136086","https://openalex.org/W2187089797","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2289394825","https://openalex.org/W2289731793","https://openalex.org/W2293634267","https://openalex.org/W2394882406","https://openalex.org/W2407793339","https://openalex.org/W2508162385","https://openalex.org/W2510867321","https://openalex.org/W2511131004","https://openalex.org/W2550928100","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/W2953127297","https://openalex.org/W2963266252","https://openalex.org/W2963826681","https://openalex.org/W2964182776","https://openalex.org/W3112742522","https://openalex.org/W3125118953","https://openalex.org/W4320013936","https://openalex.org/W6633793729","https://openalex.org/W6639480849","https://openalex.org/W6639822467","https://openalex.org/W6713823255","https://openalex.org/W6725448924","https://openalex.org/W6745924425","https://openalex.org/W6750565094"],"related_works":["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","https://openalex.org/W4285785480","https://openalex.org/W2997056298"],"abstract_inverted_index":{"We":[0,36],"propose":[1],"a":[2,28,45,50,88],"novel":[3],"adversarial":[4,83],"multi-task":[5,84],"learning":[6],"scheme,":[7],"aiming":[8],"at":[9],"actively":[10],"curtailing":[11],"the":[12,25,38,59,69,119,122,133,143,154],"inter-talker":[13],"feature":[14,78],"variability":[15],"while":[16],"maximizing":[17],"its":[18,98],"senone":[19,60],"discriminability":[20],"so":[21],"as":[22],"to":[23,57],"enhance":[24],"performance":[26],"of":[27],"deep":[29,77],"neural":[30],"network":[31,53],"(DNN)":[32],"based":[33],"ASR":[34],"system.":[35],"call":[37],"scheme":[39],"speaker-invariant":[40,74],"training":[41,114],"(SIT).":[42],"In":[43],"SIT,":[44,87],"DNN":[46,90],"acoustic":[47,91,136,157],"model":[48,92,147],"and":[49,66,75],"speaker":[51,70,141],"classifier":[52],"are":[54],"jointly":[55],"optimized":[56],"minimize":[58],"(tied":[61],"triphone":[62],"state)":[63],"classification":[64,71],"loss,":[65],"simultaneously":[67],"mini-maximize":[68],"loss.":[72],"A":[73],"senone-discriminative":[76],"is":[79,101],"learned":[80,102],"through":[81],"this":[82],"learning.":[85],"With":[86,138],"canonical":[89],"with":[93,103],"significantly":[94],"reduced":[95],"variance":[96],"in":[97,113],"output":[99],"probabilities":[100],"no":[104],"explicit":[105],"speaker-independent":[106],"(SI)":[107],"transformations":[108],"or":[109,115],"speaker-specific":[110],"representations":[111],"used":[112],"testing.":[116],"Evaluated":[117],"on":[118],"CHiME-3":[120],"dataset,":[121],"SIT":[123,146],"achieves":[124,148],"4.99%":[125],"relative":[126,150],"word":[127],"error":[128],"rate":[129],"(WER)":[130],"improvement":[131],"over":[132,153],"conventional":[134],"SI":[135,156],"model.":[137,158],"additional":[139],"unsupervised":[140],"adaptation,":[142],"speaker-adapted":[144],"(SA)":[145],"4.86%":[149],"WER":[151],"gain":[152],"SA":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":7}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}