{"id":"https://openalex.org/W3152221657","doi":"https://doi.org/10.1109/slt48900.2021.9383515","title":"Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition","display_name":"Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3152221657","doi":"https://doi.org/10.1109/slt48900.2021.9383515","mag":"3152221657"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/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":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102376243","display_name":"Sarangarajan Parthasarathy","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":"Sarangarajan Parthasarathy","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090360853","display_name":"Eric Sun","orcid":"https://orcid.org/0000-0001-8805-9864"},"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":"Eric Sun","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"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":"Liang Lu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-5801-2571"},"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":"Xie Chen","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"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":"Rui Zhao","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"250"},"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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":0.8040850758552551},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6474826335906982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6261743903160095},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5578354001045227},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5507503747940063},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5098730325698853},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5095670223236084},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5002470016479492},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4601403474807739},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4297920763492584},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4178309142589569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39583414793014526},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2579837441444397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07575923204421997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040850758552551},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6474826335906982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6261743903160095},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5578354001045227},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5507503747940063},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5098730325698853},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5095670223236084},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5002470016479492},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4601403474807739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4297920763492584},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4178309142589569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39583414793014526},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2579837441444397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07575923204421997},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1513820424","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2010362084","https://openalex.org/W2080005694","https://openalex.org/W2094147890","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2120861206","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2508162385","https://openalex.org/W2510867321","https://openalex.org/W2515801922","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2584667682","https://openalex.org/W2592356860","https://openalex.org/W2636483419","https://openalex.org/W2769025471","https://openalex.org/W2787663903","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2888779557","https://openalex.org/W2891980359","https://openalex.org/W2899771611","https://openalex.org/W2911629330","https://openalex.org/W2936252403","https://openalex.org/W2939111082","https://openalex.org/W2939164678","https://openalex.org/W2950797609","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963174344","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963970535","https://openalex.org/W2972621414","https://openalex.org/W2972818416","https://openalex.org/W2973138437","https://openalex.org/W2987019345","https://openalex.org/W3006806348","https://openalex.org/W3007328579","https://openalex.org/W3008008574","https://openalex.org/W3008037978","https://openalex.org/W3015194534","https://openalex.org/W3015915933","https://openalex.org/W3016234571","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3112742522","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6638575559","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6640090968","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6678040779","https://openalex.org/W6712847557","https://openalex.org/W6728910023","https://openalex.org/W6732447497","https://openalex.org/W6732862412","https://openalex.org/W6745924425","https://openalex.org/W6756040250","https://openalex.org/W6758052375","https://openalex.org/W6770245836","https://openalex.org/W6775605244","https://openalex.org/W6779264309","https://openalex.org/W6780226713","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2244609359"],"abstract_inverted_index":{"The":[0,122],"external":[1,46,120],"language":[2,25],"models":[3,52],"(LM)":[4],"integration":[5,43],"remains":[6],"a":[7,40],"challenging":[8],"task":[9],"for":[10],"end-to-end":[11],"(E2E)":[12],"automatic":[13],"speech":[14],"recognition":[15],"(ASR)":[16],"which":[17],"has":[18],"no":[19,54],"clear":[20],"division":[21],"between":[22,111,146],"acoustic":[23,138],"and":[24,67,105,118,148,161,169,182],"models.":[26,71],"In":[27],"this":[28],"work,":[29],"we":[30],"propose":[31],"an":[32,76,81,100,132],"internal":[33,82,96,123],"LM":[34,47,83,97,124],"estimation":[35],"(ILME)":[36],"method":[37],"to":[38,167],"facilitate":[39],"more":[41],"effective":[42],"of":[44,99,114,131],"the":[45,59,86,90,95,108,112,115,119,129,143,152],"with":[48,53,73,157],"all":[49],"pre-existing":[50],"E2E":[51,77,101,116,133,154],"additional":[55],"model":[56,78,102,117,134],"training,":[57],"including":[58],"most":[60],"popular":[61],"recurrent":[62],"neural":[63],"network":[64],"transducer":[65],"(RNN-T)":[66],"attention-based":[68],"encoder-decoder":[69],"(AED)":[70],"Trained":[72],"audio-transcript":[74],"pairs,":[75],"implicitly":[79],"learns":[80],"that":[84],"characterizes":[85],"training":[87,147],"data":[88],"in":[89],"source":[91],"domain.":[92],"With":[93],"ILME,":[94],"scores":[98,113,125],"are":[103,126],"estimated":[104],"subtracted":[106],"from":[107,176],"log-linear":[109],"interpolation":[110],"LM.":[121],"approximated":[127],"as":[128],"output":[130],"when":[135],"eliminating":[136],"its":[137],"components.":[139],"ILME":[140,164],"can":[141],"alleviate":[142],"domain":[144],"mismatch":[145],"testing,":[149],"or":[150],"improve":[151],"multi-domain":[153],"ASR.":[155],"Experimented":[156],"30K-hour":[158],"trained":[159],"RNN-T":[160],"AED":[162],"models,":[163],"achieves":[165],"up":[166],"15.5%":[168],"6.8%":[170],"relative":[171],"word":[172],"error":[173],"rate":[174],"reductions":[175],"Shallow":[177],"Fusion":[178],"on":[179],"out-of-domain":[180],"LibriSpeech":[181],"in-domain":[183],"Microsoft":[184],"production":[185],"test":[186],"sets,":[187],"respectively.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":16}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}