{"id":"https://openalex.org/W3032901281","doi":"https://doi.org/10.21437/interspeech.2020-2986","title":"Contextual RNN-T for Open Domain ASR","display_name":"Contextual RNN-T for Open Domain ASR","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3032901281","doi":"https://doi.org/10.21437/interspeech.2020-2986","mag":"3032901281"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2986","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2006.03411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112701957","display_name":"Mahaveer Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Mahaveer Jain","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048538280","display_name":"Gil Keren","orcid":"https://orcid.org/0000-0002-5153-3494"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gil Keren","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051165898","display_name":"Yatharth Saraf","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yatharth Saraf","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112701957"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.6802,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76256775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"15"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.8586148023605347},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7358834147453308},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6687849760055542},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6408029198646545},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6327064037322998},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6015962958335876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5860759615898132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5410853624343872},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5352742075920105},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4567602276802063},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.43313831090927124},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42594751715660095},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4233074188232422},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25074076652526855},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10867464542388916},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08153808116912842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586148023605347},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7358834147453308},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6687849760055542},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6408029198646545},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6327064037322998},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6015962958335876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5860759615898132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410853624343872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5352742075920105},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4567602276802063},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.43313831090927124},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42594751715660095},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4233074188232422},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25074076652526855},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10867464542388916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08153808116912842},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2986","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.03411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.03411","pdf_url":"https://arxiv.org/pdf/2006.03411","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":"","raw_type":"text"},{"id":"mag:3032901281","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.03411.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.2006.03411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.03411","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:2006.03411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.03411","pdf_url":"https://arxiv.org/pdf/2006.03411","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3032901281.pdf","grobid_xml":"https://content.openalex.org/works/W3032901281.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1553004968","https://openalex.org/W1665214252","https://openalex.org/W1828163288","https://openalex.org/W2046932483","https://openalex.org/W2127141656","https://openalex.org/W2184045248","https://openalex.org/W2327501763","https://openalex.org/W2885185669","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2936774411","https://openalex.org/W2937402758","https://openalex.org/W2962707338","https://openalex.org/W2962760690","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3095962459"],"related_works":["https://openalex.org/W3097794466","https://openalex.org/W3041679645","https://openalex.org/W2903250132","https://openalex.org/W3003335331","https://openalex.org/W2970671861","https://openalex.org/W2402238668","https://openalex.org/W3109672743","https://openalex.org/W3008749227","https://openalex.org/W2886319145","https://openalex.org/W3204936357","https://openalex.org/W2950548836","https://openalex.org/W3148906368","https://openalex.org/W3034252112","https://openalex.org/W3156762052","https://openalex.org/W3161801451","https://openalex.org/W2327501763","https://openalex.org/W2940322076","https://openalex.org/W3140315487","https://openalex.org/W3161525333","https://openalex.org/W3034931686"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"systems":[2],"for":[3,169],"automatic":[4],"speech":[5],"recognition":[6],"(ASR),":[7],"such":[8,79],"as":[9,80],"RNN":[10],"Transducer":[11],"(RNN-T)":[12],"and":[13,56,140],"Listen-Attend-Spell":[14],"(LAS)":[15],"blend":[16],"the":[17,47,90,95,103,146],"individual":[18],"components":[19],"of":[20,59,105,158],"a":[21,35,141,151,155],"traditional":[22],"hybrid":[23],"ASR":[24,133],"system":[25,48],"-":[26,33],"acoustic":[27],"model,":[28,30],"language":[29],"pronunciation":[31],"model":[32,92,96,139,143],"into":[34],"single":[36],"neural":[37],"network.":[38],"While":[39],"this":[40,84],"has":[41],"some":[42],"nice":[43],"advantages,":[44],"it":[45],"limits":[46],"to":[49,64,89,97,144],"be":[50],"trained":[51],"using":[52,136],"only":[53],"paired":[54],"audio":[55],"text.":[57],"Because":[58],"this,":[60],"E2E":[61],"models":[62],"tend":[63],"have":[65],"difficulties":[66],"with":[67,102,171],"correctly":[68],"recognizing":[69],"rare":[70],"words":[71],"that":[72,93,149],"are":[73],"not":[74],"frequently":[75],"seen":[76],"during":[77],"training,":[78],"entity":[81,111],"names.":[82],"In":[83],"paper,":[85],"we":[86,153],"propose":[87],"modifications":[88],"RNN-T":[91],"allow":[94],"utilize":[98],"additional":[99],"metadata":[100,148],"text":[101],"objective":[104],"improving":[106],"performance":[107],"on":[108,117,165],"these":[109],"named":[110],"words.":[112],"We":[113],"evaluate":[114],"our":[115],"approach":[116],"an":[118,130,137],"in-house":[119],"dataset":[120],"sampled":[121],"from":[122],"de-identified":[123],"public":[124],"social":[125],"media":[126],"videos,":[127],"which":[128],"represent":[129],"open":[131],"domain":[132],"task.":[134],"By":[135],"attention":[138],"biasing":[142],"leverage":[145],"contextual":[147],"accompanies":[150],"video,":[152],"observe":[154],"relative":[156],"improvement":[157],"about":[159],"16%":[160],"in":[161],"Word":[162],"Error":[163],"Rate":[164],"Named":[166],"Entities":[167],"(WER-NE)":[168],"videos":[170],"related":[172],"metadata.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}