{"id":"https://openalex.org/W3107588252","doi":"https://doi.org/10.1109/asru51503.2021.9688282","title":"Multi-Task Language Modeling for Improving Speech Recognition of Rare Words","display_name":"Multi-Task Language Modeling for Improving Speech Recognition of Rare Words","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3107588252","doi":"https://doi.org/10.1109/asru51503.2021.9688282","mag":"3107588252"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688282","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.11715","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031896207","display_name":"Linda Liu","orcid":"https://orcid.org/0000-0003-3687-9291"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linda Liu","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014054572","display_name":"Ankur Gandhe","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Gandhe","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022646825","display_name":"Yile Gu","orcid":"https://orcid.org/0000-0003-3662-5056"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yile Gu","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046112","display_name":"Anirudh Raju","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017041805","display_name":"Denis Filimonov","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denis Filimonov","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109934165","display_name":"Ivan Bulyko","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Bulyko","raw_affiliation_strings":["Amazon,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020376803"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.3808,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56667591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1087","last_page":"1093"},"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8829015493392944},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7351208925247192},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7224767208099365},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7178122997283936},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.659255862236023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.658816933631897},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6134482622146606},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5609604716300964},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5330957770347595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4847969114780426},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45639556646347046},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4458940327167511},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20243459939956665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8829015493392944},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7351208925247192},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7224767208099365},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7178122997283936},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.659255862236023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.658816933631897},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6134482622146606},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5609604716300964},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5330957770347595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4847969114780426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45639556646347046},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4458940327167511},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20243459939956665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688282","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.11715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.11715","pdf_url":"https://arxiv.org/pdf/2011.11715","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3107588252","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.11715.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.11715","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.11715","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.11715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.11715","pdf_url":"https://arxiv.org/pdf/2011.11715","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3107588252.pdf","grobid_xml":"https://content.openalex.org/works/W3107588252.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1550863320","https://openalex.org/W1567125377","https://openalex.org/W1828163288","https://openalex.org/W1971034924","https://openalex.org/W2064675550","https://openalex.org/W2093825590","https://openalex.org/W2094472029","https://openalex.org/W2121879602","https://openalex.org/W2124895976","https://openalex.org/W2147880316","https://openalex.org/W2327501763","https://openalex.org/W2400801499","https://openalex.org/W2800921391","https://openalex.org/W2911300548","https://openalex.org/W2954716088","https://openalex.org/W2963050422","https://openalex.org/W2963371670","https://openalex.org/W2963974889","https://openalex.org/W2970611152","https://openalex.org/W2972320704","https://openalex.org/W2973122799","https://openalex.org/W3011339933","https://openalex.org/W3014522660","https://openalex.org/W3015707549","https://openalex.org/W3015927303","https://openalex.org/W3016006013","https://openalex.org/W3016188195","https://openalex.org/W3049038774","https://openalex.org/W3094979069","https://openalex.org/W3161000786","https://openalex.org/W3161860537","https://openalex.org/W3172443934","https://openalex.org/W3192803528","https://openalex.org/W3198781161","https://openalex.org/W6629930100","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6750523955","https://openalex.org/W6758026734","https://openalex.org/W6796456916","https://openalex.org/W6800150759"],"related_works":["https://openalex.org/W3016188195","https://openalex.org/W3105804405","https://openalex.org/W3015747801","https://openalex.org/W2972320704","https://openalex.org/W3034311908","https://openalex.org/W3011207290","https://openalex.org/W3116876565","https://openalex.org/W3094180720","https://openalex.org/W3194100261","https://openalex.org/W1998080077","https://openalex.org/W2998386507","https://openalex.org/W2888760383","https://openalex.org/W2523776537","https://openalex.org/W3023953056","https://openalex.org/W3108216882","https://openalex.org/W3161525333","https://openalex.org/W2972889948","https://openalex.org/W3014528057","https://openalex.org/W2963236196","https://openalex.org/W3023895054"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,78],"recognition":[3,79],"(ASR)":[4],"systems":[5,26],"are":[6],"increasingly":[7],"popular":[8],"due":[9],"to":[10,76],"their":[11],"relative":[12,122],"architectural":[13],"simplicity":[14],"and":[15,73,109],"competitive":[16],"performance.":[17,80],"However,":[18],"even":[19],"though":[20],"the":[21,30,93,100],"average":[22],"accuracy":[23],"of":[24,120],"these":[25,89],"may":[27],"be":[28],"high,":[29],"performance":[31],"on":[32,105,112],"rare":[33,114,143],"content":[34],"words":[35,144],"often":[36,49],"lags":[37],"behind":[38],"hybrid":[39],"ASR":[40,126,140],"systems.":[41],"To":[42],"address":[43],"this":[44,57],"problem,":[45],"second-pass":[46,62],"rescoring":[47,85,95],"is":[48],"applied":[50],"leveraging":[51],"upon":[52],"language":[53],"modeling":[54],"(LM).":[55],"In":[56],"paper,":[58],"we":[59],"propose":[60],"a":[61,106,113],"system":[63,127],"with":[64,88,98,128,136],"multi-task":[65,129],"learning,":[66],"utilizing":[67],"semantic":[68],"targets":[69],"(such":[70],"as":[71],"intent":[72],"slot":[74],"prediction)":[75],"improve":[77],"We":[81],"show":[82],"that":[83],"our":[84],"model":[86],"trained":[87,97],"additional":[90],"tasks":[91],"outperforms":[92],"baseline":[94,141],"model,":[96],"only":[99,139],"LM":[101,130],"task,":[102],"by":[103,110],"1.4%":[104],"general":[107],"test":[108,116],"2.6%":[111],"word":[115],"set":[117],"in":[118],"terms":[119],"word-error-rate":[121],"(WERR).":[123],"Our":[124],"best":[125],"shows":[131],"4.6%":[132],"WERR":[133],"deduction":[134],"compared":[135],"RNN":[137],"Transducer":[138],"for":[142],"recognition.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}