{"id":"https://openalex.org/W3008008574","doi":"https://doi.org/10.1109/asru46091.2019.9003776","title":"Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition","display_name":"Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008008574","doi":"https://doi.org/10.1109/asru46091.2019.9003776","mag":"3008008574"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003776","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/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":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","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":"Yashesh Gaur","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":4,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.4805,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.9573179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.7417426705360413},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6077117919921875},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5193277597427368},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5161824822425842},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4923807382583618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48870256543159485},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4788767695426941},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4773695170879364},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44444987177848816},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43362706899642944},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4250667691230774},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.416156530380249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3635910749435425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09355431795120239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7417426705360413},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6077117919921875},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5193277597427368},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5161824822425842},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4923807382583618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48870256543159485},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4788767695426941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4773695170879364},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44444987177848816},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43362706899642944},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4250667691230774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.416156530380249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3635910749435425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09355431795120239},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003776","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1924770834","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2289394825","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2507699225","https://openalex.org/W2510867321","https://openalex.org/W2577366047","https://openalex.org/W2587088898","https://openalex.org/W2606833507","https://openalex.org/W2636483419","https://openalex.org/W2680270903","https://openalex.org/W2711861986","https://openalex.org/W2769025471","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2888858245","https://openalex.org/W2889129739","https://openalex.org/W2889500840","https://openalex.org/W2899771611","https://openalex.org/W2936252403","https://openalex.org/W2938486422","https://openalex.org/W2939164678","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962894366","https://openalex.org/W2963266252","https://openalex.org/W2963523217","https://openalex.org/W2963681135","https://openalex.org/W2963736842","https://openalex.org/W2963970535","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W2972621414","https://openalex.org/W2973138437","https://openalex.org/W3006806348","https://openalex.org/W3112742522","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6712847557","https://openalex.org/W6743562081","https://openalex.org/W6745924425","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W2088845016","https://openalex.org/W589102260","https://openalex.org/W1966421350","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W1868434454"],"abstract_inverted_index":{"Teacher-student":[0],"(T/S)":[1],"has":[2],"shown":[3],"to":[4,29,112],"be":[5],"effective":[6],"for":[7,156],"domain":[8,32,157],"adaptation":[9,33],"of":[10,34,43,66,76,108,123,140,181],"deep":[11],"neural":[12],"network":[13],"acoustic":[14],"models":[15],"in":[16,91],"hybrid":[17],"speech":[18],"recognition":[19],"systems.":[20],"In":[21],"this":[22],"work,":[23],"we":[24,69],"extend":[25],"the":[26,64,81,87,93,99,102,113,119,124,141,178],"T/S":[27,61,72,159],"learning":[28,62],"large-scale":[30],"unsupervised":[31],"an":[35],"attention-based":[36],"end-to-end":[37],"(E2E)":[38],"model":[39,175],"through":[40],"two":[41],"levels":[42],"knowledge":[44,125],"transfer:":[45],"teacher's":[46,82],"token":[47,84],"posteriors":[48,85],"as":[49,55,137],"soft":[50,83,114,142],"labels":[51,117],"and":[52,101,115,143,151,160,164],"one-best":[53],"predictions":[54],"decoder":[56,135],"guidance.":[57],"To":[58],"further":[59],"improve":[60],"with":[63,105,177],"help":[65],"ground-truth":[67,89],"labels,":[68],"propose":[70],"adaptive":[71,109],"(AT/S)":[73],"learning.":[74],"Instead":[75],"conditionally":[77],"choosing":[78],"from":[79,97],"either":[80],"or":[86],"one-hot":[88,116,144],"label,":[90],"AT/S,":[92],"student":[94],"always":[95],"learns":[96],"both":[98],"teacher":[100],"ground":[103],"truth":[104],"a":[106,138,172],"pair":[107],"weights":[110],"assigned":[111],"quantifying":[118],"confidence":[120,128],"on":[121],"each":[122,134],"sources.":[126],"The":[127],"scores":[129],"are":[130],"dynamically":[131],"estimated":[132],"at":[133],"step":[136],"function":[139],"labels.":[145],"With":[146],"3400":[147],"hours":[148],"parallel":[149],"close-talk":[150],"far-field":[152,182],"Microsoft":[153],"Cortana":[154],"data":[155],"adaptation,":[158],"AT/S":[161],"achieves":[162],"6.3%":[163],"10.3%":[165],"relative":[166],"word":[167],"error":[168],"rate":[169],"improvement":[170],"over":[171],"strong":[173],"E2E":[174],"trained":[176],"same":[179],"amount":[180],"data.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}