{"id":"https://openalex.org/W4319862708","doi":"https://doi.org/10.1109/slt54892.2023.10023407","title":"Dual Learning for Large Vocabulary On-Device ASR","display_name":"Dual Learning for Large Vocabulary On-Device ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862708","doi":"https://doi.org/10.1109/slt54892.2023.10023407"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023407","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023407","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/A5037066965","display_name":"Cal Peyser","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"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cal Peyser","raw_affiliation_strings":["New York University,Center for Data Science,New York City,USA","Center for Data Science, New York University, New York City, USA","Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science,New York City,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University, New York City, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006141298","display_name":"Ronny Huang","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":"Ronny Huang","raw_affiliation_strings":["Google Inc.,U.S.A","Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 Sainath","raw_affiliation_strings":["Google Inc.,U.S.A","Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., U.S.A","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.,U.S.A","Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["New York University,Center for Data Science,New York City,USA","Center for Data Science, New York University, New York City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science,New York City,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University, New York City, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057911829","display_name":"Kyunghyun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":["New York University,Center for Data Science,New York City,USA","Center for Data Science, New York University, New York City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science,New York City,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University, New York City, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0073941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1503 3535","issue":null,"first_page":"245","last_page":"251"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"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/leverage","display_name":"Leverage (statistics)","score":0.7914232015609741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7900631427764893},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6341283321380615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6291987299919128},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6140130162239075},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5421209931373596},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5162953734397888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5122427344322205},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.47122111916542053},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4662296772003174},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4544416666030884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4402763247489929},{"id":"https://openalex.org/keywords/pairing","display_name":"Pairing","score":0.4218358099460602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3756556808948517},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14199921488761902}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7914232015609741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900631427764893},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6341283321380615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6291987299919128},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6140130162239075},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5421209931373596},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5162953734397888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5122427344322205},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.47122111916542053},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4662296772003174},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4544416666030884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4402763247489929},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.4218358099460602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3756556808948517},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14199921488761902},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C54101563","wikidata":"https://www.wikidata.org/wiki/Q124131","display_name":"Superconductivity","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023407","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023407","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":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W82886505","https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W648786980","https://openalex.org/W1915251500","https://openalex.org/W1975113979","https://openalex.org/W2140914930","https://openalex.org/W2546938941","https://openalex.org/W2842511635","https://openalex.org/W2886095922","https://openalex.org/W2888779557","https://openalex.org/W2936774411","https://openalex.org/W2962699523","https://openalex.org/W2963739817","https://openalex.org/W2964243274","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W3015280134","https://openalex.org/W3015356564","https://openalex.org/W3016234571","https://openalex.org/W3036601975","https://openalex.org/W3081416955","https://openalex.org/W3096815019","https://openalex.org/W3097286738","https://openalex.org/W3097777922","https://openalex.org/W3100270690","https://openalex.org/W3163203022","https://openalex.org/W3197976839","https://openalex.org/W3198858531","https://openalex.org/W3209984917","https://openalex.org/W4210690962","https://openalex.org/W4225272718","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6640059789","https://openalex.org/W6680972403","https://openalex.org/W6729383884","https://openalex.org/W6739901393","https://openalex.org/W6741328424","https://openalex.org/W6747636377","https://openalex.org/W6755207826","https://openalex.org/W6762242920","https://openalex.org/W6769238691","https://openalex.org/W6769593479","https://openalex.org/W6770514103"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W34092691","https://openalex.org/W4312414840","https://openalex.org/W2096363773","https://openalex.org/W2794908468","https://openalex.org/W2531570999","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W2553312496","https://openalex.org/W4319302697"],"abstract_inverted_index":{"Dual":[0,43,85],"learning":[1,8,44,86],"is":[2,27],"a":[3],"paradigm":[4],"for":[5,32,74,93],"semi-supervised":[6],"machine":[7],"that":[9,35,103],"seeks":[10],"to":[11,29,38,72,97],"leverage":[12],"unsupervised":[13,95],"data":[14,96],"by":[15,52],"solving":[16],"two":[17],"opposite":[18],"tasks":[19],"at":[20],"once.":[21],"In":[22],"this":[23,113],"scheme,":[24],"each":[25],"model":[26],"used":[28,37],"generate":[30],"pseudo-labels":[31],"unlabeled":[33],"examples":[34,71],"are":[36,104],"train":[39],"the":[40,66,126],"other":[41],"model.":[42],"has":[45,87],"seen":[46],"some":[47],"use":[48],"in":[49],"speech":[50],"processing":[51],"pairing":[53],"ASR":[54],"and":[55,79,139],"TTS":[56],"as":[57],"dual":[58],"tasks.":[59],"However,":[60],"these":[61],"results":[62],"mostly":[63,80],"address":[64],"only":[65],"case":[67],"of":[68,119,128,134],"using":[69,94],"unpaired":[70],"compensate":[73],"very":[75],"small":[76],"supervised":[77,109],"datasets,":[78],"on":[81,107,125],"large,":[82],"non-streaming":[83],"models.":[84],"not":[88],"yet":[89],"been":[90],"proven":[91],"effective":[92],"improve":[98],"realistic":[99],"on-device":[100],"streaming":[101,122],"models":[102],"already":[105],"trained":[106,124],"large":[108],"corpora.":[110],"We":[111],"provide":[112],"missing":[114],"piece":[115],"though":[116],"an":[117,120,137,142],"analysis":[118],"on-device-sized":[121],"conformer":[123],"entirety":[127],"Librispeech,":[129],"showing":[130],"relative":[131],"WER":[132],"improvements":[133],"10.7%/5.2%":[135],"without":[136],"LM":[138],"11.7%/16.4%":[140],"with":[141],"LM.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}