{"id":"https://openalex.org/W4226093136","doi":"https://doi.org/10.1109/icassp43922.2022.9746554","title":"Usted: Improving ASR with a Unified Speech and Text Encoder-Decoder","display_name":"Usted: Improving ASR with a Unified Speech and Text Encoder-Decoder","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226093136","doi":"https://doi.org/10.1109/icassp43922.2022.9746554"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5007614006","display_name":"Bolaji Yusuf","orcid":"https://orcid.org/0000-0001-9852-3456"},"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":"Bolaji Yusuf","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, 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 Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077849031","display_name":"Alex Sokolov","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":"Alex Sokolov","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.8304,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73299761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8297","last_page":"8301"},"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/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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.7998605966567993},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7116580009460449},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7097642421722412},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6936361193656921},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6649509072303772},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6253357529640198},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5833628177642822},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5199095606803894},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4579450488090515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.451978862285614},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45120206475257874},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4266171455383301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39344534277915955},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07458370923995972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998605966567993},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7116580009460449},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7097642421722412},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6936361193656921},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6649509072303772},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6253357529640198},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5833628177642822},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5199095606803894},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4579450488090515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.451978862285614},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45120206475257874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4266171455383301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39344534277915955},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07458370923995972},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1915251500","https://openalex.org/W2124558353","https://openalex.org/W2327501763","https://openalex.org/W2419539795","https://openalex.org/W2577366047","https://openalex.org/W2962699523","https://openalex.org/W2962826786","https://openalex.org/W2963979492","https://openalex.org/W2972889948","https://openalex.org/W3008037978","https://openalex.org/W3015280134","https://openalex.org/W3015449694","https://openalex.org/W3015522062","https://openalex.org/W3016234571","https://openalex.org/W3033038061","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3161143478","https://openalex.org/W3163464943","https://openalex.org/W3163560333","https://openalex.org/W3197681820","https://openalex.org/W3198836239","https://openalex.org/W4288089799","https://openalex.org/W6640059789","https://openalex.org/W6717262007","https://openalex.org/W6769627184","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2794347674","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Improving":[0],"end-to-end":[1],"speech":[2],"recognition":[3],"by":[4],"incorporating":[5],"external":[6,32,43],"text":[7,33,136],"data":[8,34,91,137,153],"has":[9,16],"been":[10,17],"a":[11,18,59,69,125],"longstanding":[12],"research":[13],"topic.":[14],"There":[15],"recent":[19],"focus":[20],"on":[21,101,151,168],"training":[22,54],"E2E":[23],"ASR":[24,55,80],"models":[25],"that":[26],"get":[27],"the":[28,37,74,86,131,134,161,169],"performance":[29,167],"benefits":[30],"of":[31,40,61,73,97,119],"without":[35,110,164],"incurring":[36],"extra":[38,112],"cost":[39,113],"evaluating":[41],"an":[42,107],"language":[44,83,149],"model":[45,56,84,150],"at":[46,114],"inference":[47,115],"time.":[48],"In":[49],"this":[50],"work,":[51],"we":[52,77,93,146,156],"propose":[53],"jointly":[57,78],"with":[58,65,85,133],"set":[60],"text-to-text":[62],"auxiliary":[63,162],"tasks":[64],"which":[66,129],"it":[67],"shares":[68],"decoder":[70,132],"and":[71,81,89,99,103,117,121],"parts":[72],"encoder.":[75],"When":[76],"train":[79,147],"masked":[82,148],"960-hour":[87],"Librispeech":[88,152],"Opensubtitles":[90],"respectively,":[92],"observe":[94],"WER":[95],"reductions":[96,118],"16%":[98],"20%":[100],"test-other":[102],"test-clean":[104],"respectively":[105],"over":[106],"ASR-only":[108],"baseline":[109,128],"any":[111],"time,":[116],"6%":[120],"8%":[122],"compared":[123],"to":[124],"stronger":[126],"MUTE-L":[127],"trains":[130],"same":[135],"as":[138,160],"our":[139],"model.":[140],"We":[141],"achieve":[142],"further":[143],"improvements":[144],"when":[145,155],"or":[154],"use":[157],"machine":[158],"translation":[159],"task,":[163],"significantly":[165],"sacrificing":[166],"task":[170],"itself.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}