{"id":"https://openalex.org/W3015556645","doi":"https://doi.org/10.1109/icassp40776.2020.9053510","title":"An Attention-Based Joint Acoustic and Text on-Device End-To-End Model","display_name":"An Attention-Based Joint Acoustic and Text on-Device End-To-End Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015556645","doi":"https://doi.org/10.1109/icassp40776.2020.9053510","mag":"3015556645"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112901893","display_name":"Ruoming Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruoming Pang","raw_affiliation_strings":["Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung-cheng Chiu","raw_affiliation_strings":["Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Strohman","raw_affiliation_strings":["Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070513394"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.3256,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84471913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7039","last_page":"7043"},"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":0.9997000098228455,"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":0.9991000294685364,"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":0.8000578284263611},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6525735855102539},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6192821860313416},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6100016236305237},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.5852009057998657},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5507397651672363},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4863153398036957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4595995545387268},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45801204442977905},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4136797785758972},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37677717208862305},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1868727207183838},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14345523715019226},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07321274280548096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000578284263611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6525735855102539},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6192821860313416},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6100016236305237},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.5852009057998657},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5507397651672363},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4863153398036957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595995545387268},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45801204442977905},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4136797785758972},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37677717208862305},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1868727207183838},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14345523715019226},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07321274280548096},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2121879602","https://openalex.org/W2271840356","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2769810959","https://openalex.org/W2888779557","https://openalex.org/W2928941594","https://openalex.org/W2940322076","https://openalex.org/W2945078028","https://openalex.org/W2952711665","https://openalex.org/W2962704885","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962893195","https://openalex.org/W2963216553","https://openalex.org/W2963240019","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963442512","https://openalex.org/W2963739817","https://openalex.org/W2963782041","https://openalex.org/W2964012862","https://openalex.org/W2964309797","https://openalex.org/W2972625221","https://openalex.org/W2972991710","https://openalex.org/W2973122799","https://openalex.org/W3008181812","https://openalex.org/W4294619240","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6694517276","https://openalex.org/W6728030952","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6747398299","https://openalex.org/W6760633627","https://openalex.org/W6762242920"],"related_works":["https://openalex.org/W2949174760","https://openalex.org/W2126322296","https://openalex.org/W2916997151","https://openalex.org/W2163537793","https://openalex.org/W3198455051","https://openalex.org/W2781555308","https://openalex.org/W4386794561","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210"],"abstract_inverted_index":{"Recently,":[0],"we":[1,84],"introduced":[2],"a":[3,23,38,66,71,76,86,103,118,126,136],"two-pass":[4],"on-device":[5,32],"end-to-end":[6],"(E2E)":[7],"speech":[8],"recognition":[9],"model,":[10],"which":[11,69,97],"runs":[12],"RNN-T":[13],"in":[14,117,122],"the":[15,20,94,113],"first-pass":[16],"and":[17,27,57,89],"then":[18],"rescores/redecodes":[19],"result":[21],"using":[22],"noncausal":[24],"Listen,":[25],"Attend":[26],"Spell":[28],"(LAS)":[29],"decoder.":[30],"This":[31],"model":[33,68,73,115],"obtained":[34],"similar":[35],"performance":[36],"to":[37,65,101,125],"state-of-the-art":[39],"conventional":[40,67],"model.":[41],"However,":[42],"like":[43],"many":[44],"E2E":[45],"models,":[46],"it":[47,99],"suffers":[48],"from":[49],"being":[50],"trained":[51,74,129],"only":[52,130],"on":[53,61,75,131],"supervised":[54,132],"audio-text":[55,133],"pairs":[56,134],"thus":[58],"performs":[59],"poorly":[60],"rare":[62],"words":[63],"compared":[64,124],"incorporates":[70],"language":[72],"much":[77,104],"larger":[78,105],"text":[79,90,106],"corpus.":[80],"In":[81],"this":[82],"work,":[83],"introduce":[85],"joint":[87],"acoustic":[88],"decoder":[91,128],"(JATD)":[92],"into":[93,108],"LAS":[95,127],"decoder,":[96],"makes":[98],"possible":[100],"incorporate":[102],"corpus":[107],"training.":[109],"We":[110],"find":[111],"that":[112],"JATD":[114],"obtains":[116],"3-10%":[119],"relative":[120],"improvement":[121],"WER":[123],"across":[135],"variety":[137],"of":[138],"proper":[139],"noun":[140],"test":[141],"sets.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}