{"id":"https://openalex.org/W4319862474","doi":"https://doi.org/10.1109/slt54892.2023.10022774","title":"JOIST: A Joint Speech and Text Streaming Model for ASR","display_name":"JOIST: A Joint Speech and Text Streaming Model for ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862474","doi":"https://doi.org/10.1109/slt54892.2023.10022774"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022774","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.07353","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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":"Rohit Prabhavalkar","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","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":"Ankur Bapna","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433630","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-8345-3835"},"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":"Yu Zhang","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069872293","display_name":"Zhouyuan Huo","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":"Zhouyuan Huo","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"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":"Zhehuai Chen","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374521","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-4186-4828"},"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":"Bo Li","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"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":"Weiran Wang","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","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."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.952,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.782619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"59"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9999,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9999,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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/joist","display_name":"Joist","score":0.6647856},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.5140944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74226844},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6915448},{"id":"https://openalex.org/C2775926657","wikidata":"https://www.wikidata.org/wiki/Q6587065","display_name":"Joist","level":2,"score":0.6647856},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6280435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5942291},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5140944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49154314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48181358},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.47463474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.093017966},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0702351},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022774","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2210.07353","pdf_url":"https://arxiv.org/pdf/2210.07353","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2210.07353","pdf_url":"https://arxiv.org/pdf/2210.07353","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":63,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W1494198834","https://openalex.org/W2013598660","https://openalex.org/W2033256038","https://openalex.org/W2076794394","https://openalex.org/W2121879602","https://openalex.org/W2143612262","https://openalex.org/W2293634267","https://openalex.org/W2296014541","https://openalex.org/W2296545762","https://openalex.org/W2394932179","https://openalex.org/W2507771204","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2750499125","https://openalex.org/W2935756939","https://openalex.org/W2936774411","https://openalex.org/W2937402758","https://openalex.org/W2962699523","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963382687","https://openalex.org/W2963739817","https://openalex.org/W2963747784","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W3007227084","https://openalex.org/W3008181812","https://openalex.org/W3011411500","https://openalex.org/W3015556645","https://openalex.org/W3016011332","https://openalex.org/W3016234571","https://openalex.org/W3028545098","https://openalex.org/W3034999214","https://openalex.org/W3094979069","https://openalex.org/W3095311338","https://openalex.org/W3095697114","https://openalex.org/W3096815019","https://openalex.org/W3097777922","https://openalex.org/W3160235762","https://openalex.org/W3160766462","https://openalex.org/W3163907627","https://openalex.org/W3197976839","https://openalex.org/W3198442913","https://openalex.org/W3205644108","https://openalex.org/W3207222250","https://openalex.org/W3209059054","https://openalex.org/W3212799896","https://openalex.org/W4210690962","https://openalex.org/W4221155340","https://openalex.org/W4223622550","https://openalex.org/W4224916448","https://openalex.org/W4225272718","https://openalex.org/W4225307083","https://openalex.org/W4225319488","https://openalex.org/W4225529283","https://openalex.org/W4226033575","https://openalex.org/W4226093136","https://openalex.org/W4226120743","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W635256691","https://openalex.org/W4235400283","https://openalex.org/W3183649803","https://openalex.org/W3160505215","https://openalex.org/W2373842031","https://openalex.org/W2321178748","https://openalex.org/W2080163376","https://openalex.org/W1908610925","https://openalex.org/W1844410701","https://openalex.org/W134068554"],"abstract_inverted_index":{"We":[0,93],"present":[1],"JOIST,":[2],"an":[3,49],"algorithm":[4],"to":[5,60,78,116],"train":[6],"a":[7,44,64,104,117],"streaming,":[8],"cascaded,":[9],"encoder":[10],"end-to-end":[11],"(E2E)":[12],"model":[13,47,79,118],"with":[14,30,48,121],"both":[15,31],"speech-text":[16],"paired":[17],"inputs,":[18],"and":[19,36,86,108],"text-only":[20],"unpaired":[21],"inputs.":[22],"Unlike":[23],"previous":[24,61],"works,":[25],"we":[26,40,69,125],"explore":[27,41,70],"joint":[28],"training":[29],"modalities,":[32],"rather":[33],"than":[34],"pre-training":[35],"fine-tuning.":[37],"In":[38,123],"addition,":[39,124],"JOIST":[42,100,129],"using":[43],"streaming":[45,131],"E2E":[46],"order":[50],"of":[51,66,73,82,106],"magnitude":[52],"more":[53],"data,":[54],"which":[55,133],"are":[56],"also":[57],"novelties":[58],"compared":[59,115],"works.":[62],"Through":[63],"series":[65],"ablation":[67],"studies,":[68],"different":[71],"types":[72],"text":[74,84,89,97],"modeling,":[75],"including":[76],"how":[77],"the":[80,83,87],"length":[81],"sequence":[85],"appropriate":[88],"subword":[90],"unit":[91],"representation.":[92],"find":[94],"that":[95,128],"best":[96],"representation":[98],"for":[99,136],"improves":[101],"WER":[102],"across":[103],"variety":[105],"search":[107],"rare-word":[109],"test":[110],"sets":[111],"by":[112],"4-14%":[113],"relative,":[114],"not":[119],"trained":[120],"text.":[122],"quantitatively":[126],"show":[127],"maintains":[130],"capabilities,":[132],"is":[134],"important":[135],"good":[137],"user-level":[138],"experience.":[139]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862474","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11}],"updated_date":"2025-01-19T14:21:17.462469","created_date":"2023-02-11"}