{"id":"https://openalex.org/W4225985539","doi":"https://doi.org/10.1109/asru51503.2021.9687895","title":"Context-Aware Transformer Transducer for Speech Recognition","display_name":"Context-Aware Transformer Transducer for Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4225985539","doi":"https://doi.org/10.1109/asru51503.2021.9687895"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687895","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":"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/A5102963746","display_name":"Feng-Ju Chang","orcid":"https://orcid.org/0000-0003-2405-3118"},"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":"Feng-Ju Chang","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"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":"Jing Liu","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023415990","display_name":"Martin Radfar","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":"Martin Radfar","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"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":"Athanasios Mouchtaris","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025736898","display_name":"Maurizio Omologo","orcid":"https://orcid.org/0000-0003-0879-0548"},"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":"Maurizio Omologo","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","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":"Ariya Rastrow","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","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":"Siegfried Kunzmann","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102963746"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":4.8212,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.96237752,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"503","last_page":"510"},"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":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.8429834842681885},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7391684055328369},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7152822017669678},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6773420572280884},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6309514045715332},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6101175546646118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6038175225257874},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4777985215187073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47260576486587524},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14173871278762817},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08715924620628357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429834842681885},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7391684055328369},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7152822017669678},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6773420572280884},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6309514045715332},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6101175546646118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6038175225257874},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4777985215187073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47260576486587524},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14173871278762817},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08715924620628357},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687895","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2327501763","https://openalex.org/W2403440562","https://openalex.org/W2883416004","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2903250132","https://openalex.org/W2937402758","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963979492","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W2975429091","https://openalex.org/W2976556660","https://openalex.org/W3016010032","https://openalex.org/W3095962459","https://openalex.org/W3097239815","https://openalex.org/W3097794466","https://openalex.org/W3161860537","https://openalex.org/W3163462603","https://openalex.org/W4288088457","https://openalex.org/W4327845728","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6743477263","https://openalex.org/W6755207826","https://openalex.org/W6767719158","https://openalex.org/W6769806307"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2275988210"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3],"recognition":[4,26],"(ASR)":[5],"systems":[6],"often":[7],"have":[8],"difficulty":[9],"recognizing":[10],"uncommon":[11],"words,":[12,31],"that":[13,52,127],"appear":[14],"infrequently":[15],"in":[16],"the":[17,25,54,79,82,96,117,136,141],"training":[18],"data.":[19],"One":[20],"promising":[21],"method,":[22],"to":[23,33,89,94,111],"improve":[24],"accuracy":[27],"on":[28],"such":[29,63],"rare":[30],"is":[32,75],"latch":[34],"onto":[35],"personalized/contextual":[36],"information":[37],"at":[38],"inference.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,67,125],"present":[44],"a":[45,69,130],"novel":[46],"context-aware":[47],"transformer":[48,143],"transducer":[49,144],"(CATT)":[50],"network":[51,118],"improves":[53,135],"state-of-the-art":[55],"transformer-based":[56],"ASR":[57,83],"system":[58],"by":[59,152],"taking":[60],"advantage":[61],"of":[62,81,140],"contextual":[64,91,113,150],"signals.":[65],"Specifically,":[66],"propose":[68],"multi-head":[70],"attention-based":[71],"context-biasing":[72],"network,":[73],"which":[74],"jointly":[76],"trained":[77],"with":[78],"rest":[80],"sub-networks.":[84],"We":[85,101],"explore":[86],"different":[87],"techniques":[88],"encode":[90,112],"data":[92,114],"and":[93,106,115,145,154],"create":[95],"final":[97],"attention":[98],"context":[99,133],"vectors.":[100],"also":[102],"leverage":[103],"both":[104],"BLSTM":[105],"pretrained":[107],"BERT":[108,131],"based":[109,132],"models":[110],"guide":[116],"training.":[119],"Using":[120],"an":[121,147],"in-house":[122],"far-field":[123],"dataset,":[124],"show":[126],"CATT,":[128],"using":[129],"encoder,":[134],"word":[137],"error":[138],"rate":[139],"baseline":[142],"outperforms":[146],"existing":[148],"deep":[149],"model":[151],"24.2%":[153],"19.4%":[155],"respectively.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}