{"id":"https://openalex.org/W4319862218","doi":"https://doi.org/10.1109/slt54892.2023.10022791","title":"Maestro-U: Leveraging Joint Speech-Text Representation Learning for Zero Supervised Speech ASR","display_name":"Maestro-U: Leveraging Joint Speech-Text Representation Learning for Zero Supervised Speech ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862218","doi":"https://doi.org/10.1109/slt54892.2023.10022791"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022791","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"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":"Andrew Rosenberg","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","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":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","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":"Pedro Moreno","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049929716","display_name":"Nanxin Chen","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":"Nanxin Chen","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"68","last_page":"75"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9977999925613403,"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":0.8522802591323853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5801897048950195},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5640864968299866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5329419374465942},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5149748921394348},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4970376789569855},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47686585783958435},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.468105286359787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4145182967185974},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.41179123520851135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8522802591323853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5801897048950195},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5640864968299866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329419374465942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5149748921394348},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4970376789569855},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47686585783958435},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.468105286359787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4145182967185974},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.41179123520851135},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022791","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1978660892","https://openalex.org/W2842511635","https://openalex.org/W2894835365","https://openalex.org/W2914699162","https://openalex.org/W2934852845","https://openalex.org/W2936774411","https://openalex.org/W2952809536","https://openalex.org/W2962799225","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963425185","https://openalex.org/W2964002616","https://openalex.org/W2964079874","https://openalex.org/W2971840980","https://openalex.org/W2973049979","https://openalex.org/W3015564377","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3095410713","https://openalex.org/W3110458199","https://openalex.org/W3115778530","https://openalex.org/W3119308075","https://openalex.org/W3137010024","https://openalex.org/W3161296985","https://openalex.org/W3169483174","https://openalex.org/W3198840231","https://openalex.org/W3202037040","https://openalex.org/W3207222250","https://openalex.org/W3212799896","https://openalex.org/W4210690962","https://openalex.org/W4221155340","https://openalex.org/W4225272718","https://openalex.org/W4225295099","https://openalex.org/W4226033575","https://openalex.org/W4226120743","https://openalex.org/W4287173589","https://openalex.org/W4288282820","https://openalex.org/W4297808394","https://openalex.org/W4319862635","https://openalex.org/W4319862670","https://openalex.org/W6696449567","https://openalex.org/W6757585730","https://openalex.org/W6757699909","https://openalex.org/W6760519848","https://openalex.org/W6765544429","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6784577980","https://openalex.org/W6784614252","https://openalex.org/W6795952400","https://openalex.org/W6803092890","https://openalex.org/W6810259195","https://openalex.org/W6838929754","https://openalex.org/W6849880362"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W4200068392","https://openalex.org/W2129812225","https://openalex.org/W2523799048"],"abstract_inverted_index":{"Training":[0],"state-of-the-art":[1],"Automated":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"models":[6],"typically":[7],"requires":[8],"a":[9,21,36,63,161,168],"substantial":[10],"amount":[11],"of":[12,55,75,109,139,164,170,211],"transcribed":[13,103],"speech.":[14],"In":[15],"this":[16],"work,":[17],"we":[18,94,126,142,174],"demonstrate":[19],"that":[20,128,176],"modality-matched":[22],"joint":[23],"speech":[24,46,58,83,104,131,156,186],"and":[25,59,84,112,137,207],"text":[26,60,85,135],"model":[27,40],"introduced":[28],"in":[29,62,86,107],"[1]":[30],"can":[31,113,143,178],"be":[32,114],"leveraged":[33],"to":[34,71,98,116,159,192,201],"train":[35],"massively":[37,64],"multilingual":[38],"ASR":[39,79,119],"without":[41],"any":[42],"supervised":[43,67,155,185],"(manually":[44],"transcribed)":[45],"for":[47],"some":[48],"languages.":[49,89],"This":[50],"paper":[51],"explores":[52],"the":[53,73,87,91,96,122,146,199,209],"use":[54,138],"jointly":[56],"learnt":[57],"representations":[61,132,136],"multilingual,":[65],"zero":[66],"speech,":[68],"real-world":[69],"setting":[70],"expand":[72],"set":[74],"languages":[76,111,152,173,183,213],"covered":[77],"by":[78,129,204],"with":[80,133,153,184],"only":[81],"unlabeled":[82],"target":[88],"Using":[90],"FLEURS":[92],"dataset,":[93],"define":[95],"task":[97],"cover":[99],"102":[100],"languages,":[101],"where":[102],"is":[105,190],"available":[106],"52":[108],"these":[110],"used":[115],"improve":[117],"end-to-end":[118],"quality":[120],"on":[121,151],"remaining":[123],"50.":[124],"First,":[125],"show":[127,175],"combining":[130],"byte-level":[134],"language":[140],"embeddings,":[141],"dramatically":[144],"reduce":[145],"Character":[147],"Error":[148],"Rate":[149],"(CER)":[150],"no":[154,193],"from":[157,182],"64.8%":[158],"30.8%,":[160],"relative":[162,206],"reduction":[163],"53%.":[165],"Second,":[166],"using":[167],"subset":[169],"South":[171],"Asian":[172],"Maestro-U":[177,197],"promote":[179],"knowledge":[180],"transfer":[181],"even":[187],"when":[188],"there":[189],"limited":[191],"graphemic":[194],"overlap.":[195],"Overall,":[196],"closes":[198],"gap":[200],"oracle":[202],"performance":[203],"68.5%":[205],"reduces":[208],"CER":[210],"19":[212],"below":[214],"15%.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}