{"id":"https://openalex.org/W4391021664","doi":"https://doi.org/10.1109/asru57964.2023.10389738","title":"Joint Federated Learning and Personalization for on-Device ASR","display_name":"Joint Federated Learning and Personalization for on-Device ASR","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021664","doi":"https://doi.org/10.1109/asru57964.2023.10389738"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5113970008","display_name":"Junteng Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junteng Jia","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343450","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-7200-4244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060956498","display_name":"Mani Malek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mani Malek","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112754279","display_name":"Kshitiz Malik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kshitiz Malik","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113970008"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67880951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9947999715805054,"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/personalization","display_name":"Personalization","score":0.8508760929107666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8475955724716187},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6364234685897827},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6045119762420654},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5576361417770386},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.49999260902404785},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4362821578979492},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4312629997730255},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41176721453666687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38280707597732544},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3285673260688782},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3248251676559448},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1754835844039917},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.16398116946220398}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8508760929107666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475955724716187},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6364234685897827},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6045119762420654},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5576361417770386},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.49999260902404785},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4362821578979492},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4312629997730255},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41176721453666687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38280707597732544},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3285673260688782},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3248251676559448},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1754835844039917},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16398116946220398},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/asru57964.2023.10389738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1985371235","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2160306971","https://openalex.org/W2239847623","https://openalex.org/W2394882406","https://openalex.org/W2405883473","https://openalex.org/W2535838896","https://openalex.org/W2750499125","https://openalex.org/W2896422817","https://openalex.org/W2900120080","https://openalex.org/W2904190483","https://openalex.org/W2936774411","https://openalex.org/W2962940707","https://openalex.org/W2972322676","https://openalex.org/W2972621414","https://openalex.org/W2990789643","https://openalex.org/W3018763859","https://openalex.org/W3025567392","https://openalex.org/W3030459553","https://openalex.org/W3048123939","https://openalex.org/W3097714942","https://openalex.org/W3097777922","https://openalex.org/W3112702554","https://openalex.org/W3125118953","https://openalex.org/W3129405170","https://openalex.org/W3149509723","https://openalex.org/W3158424777","https://openalex.org/W3162072286","https://openalex.org/W3162665866","https://openalex.org/W3163004056","https://openalex.org/W3194334755","https://openalex.org/W3198769601","https://openalex.org/W3201225328","https://openalex.org/W3206965164","https://openalex.org/W3207629995","https://openalex.org/W3209696639","https://openalex.org/W4225274946","https://openalex.org/W4254718357","https://openalex.org/W4287326337","https://openalex.org/W4287906413","https://openalex.org/W4288333953","https://openalex.org/W4297687186","https://openalex.org/W4297841396","https://openalex.org/W4318619660","https://openalex.org/W4378474381","https://openalex.org/W4380993062","https://openalex.org/W4385823097","https://openalex.org/W4385823224","https://openalex.org/W6638749077","https://openalex.org/W6728757088","https://openalex.org/W6755988804","https://openalex.org/W6757172675","https://openalex.org/W6759579507","https://openalex.org/W6770590064","https://openalex.org/W6772318479","https://openalex.org/W6776489473","https://openalex.org/W6790358555","https://openalex.org/W6790640957","https://openalex.org/W6790936303","https://openalex.org/W6791102956","https://openalex.org/W6802287288","https://openalex.org/W6802744804","https://openalex.org/W6803334173","https://openalex.org/W6836053404","https://openalex.org/W6840756468","https://openalex.org/W6853469695","https://openalex.org/W6853644682"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W2468279273","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3044188621","https://openalex.org/W3184035966"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,37,87],"propose":[4,38],"a":[5,19,66],"joint":[6,98],"federated":[7],"learning":[8],"(FL)":[9],"and":[10,33,57,75,106,108,115],"personalization":[11,107],"method":[12,99],"for":[13,59,112,136],"on-device":[14,44,73],"ASR":[15,24],"adaptation.":[16],"Starting":[17],"with":[18,65,120,138],"Conformer-based":[20],"RNN-T":[21],"as":[22],"the":[23,49,63,101],"model":[25],"backbone":[26,50,64],"that":[27,69],"is":[28,70],"pretrained":[29],"on":[30,51,72,78],"public":[31],"data":[32,43,54,74],"shared":[34],"across":[35],"devices,":[36],"to":[39,41,134,152],"adapt":[40],"user":[42,53],"by":[45,55],"\u2460":[46],"collectively":[47],"finetuning":[48],"all":[52],"FL,":[56],"\u2461":[58],"each":[60],"user,":[61],"augmenting":[62],"personalized":[67],"adapter":[68],"trained":[71],"stored":[76],"locally":[77],"their":[79],"devices.":[80],"As":[81],"ground-truth":[82],"transcriptions":[83],"are":[84],"not":[85],"available,":[86],"use":[88],"pseudo-label":[89],"training,":[90],"which":[91],"can":[92],"be":[93],"completely":[94],"performed":[95],"on-device.":[96],"Our":[97],"combines":[100],"best":[102],"of":[103],"both":[104,113],"FL":[105],"achieves":[109,126,144],"maximum":[110],"effect":[111],"heavy":[114],"light":[116],"users:":[117],"For":[118],"users":[119,137],"50+":[121],"adaptation":[122,140],"utterances,":[123],"our":[124,142],"recipe":[125,143],"$27.4":[127],"\\%$":[128,146],"relative":[129,147],"WER":[130,148],"reduction,":[131],"largely":[132],"due":[133,151],"personalization;":[135],"no":[139],"utterance,":[141],"$8.9":[145],"reduction":[149],"purely":[150],"FL.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}