{"id":"https://openalex.org/W3162072286","doi":"https://doi.org/10.1109/icassp39728.2021.9414305","title":"Federated Acoustic Modeling for Automatic Speech Recognition","display_name":"Federated Acoustic Modeling for Automatic Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162072286","doi":"https://doi.org/10.1109/icassp39728.2021.9414305","mag":"3162072286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM Research AI, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088593720","display_name":"Songtao Lu","orcid":"https://orcid.org/0000-0001-9256-9648"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songtao Lu","raw_affiliation_strings":["IBM Research AI, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":4.2152,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95011584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6748","last_page":"6752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250234127044678},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.7420931458473206},{"id":"https://openalex.org/keywords/service-provider","display_name":"Service provider","score":0.5324586033821106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.525283932685852},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5149275064468384},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.49331822991371155},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46816015243530273},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.44529300928115845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27780044078826904},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27363958954811096},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20879033207893372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250234127044678},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.7420931458473206},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.5324586033821106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.525283932685852},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5149275064468384},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.49331822991371155},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46816015243530273},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.44529300928115845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27780044078826904},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27363958954811096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20879033207893372},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2002342963","https://openalex.org/W2027595342","https://openalex.org/W2069631319","https://openalex.org/W2405883473","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2896422817","https://openalex.org/W2900120080","https://openalex.org/W2936012302","https://openalex.org/W3015677819","https://openalex.org/W3023974895","https://openalex.org/W3025567392","https://openalex.org/W3084415909","https://openalex.org/W3088155259","https://openalex.org/W3094793624","https://openalex.org/W3102816259","https://openalex.org/W4205228770","https://openalex.org/W4294106961","https://openalex.org/W4297687186","https://openalex.org/W4318619660","https://openalex.org/W6728757088","https://openalex.org/W6729007826","https://openalex.org/W6755988804","https://openalex.org/W6771536673","https://openalex.org/W6782794873","https://openalex.org/W6785938674"],"related_works":["https://openalex.org/W3080832531","https://openalex.org/W4214626077","https://openalex.org/W4388282301","https://openalex.org/W4385625427","https://openalex.org/W3158596343","https://openalex.org/W4285322112","https://openalex.org/W4292794239","https://openalex.org/W2186896963","https://openalex.org/W4372346152","https://openalex.org/W4361192867"],"abstract_inverted_index":{"Data":[0],"privacy":[1],"and":[2,43,54,107],"protection":[3],"is":[4,36,77,110],"a":[5,39,51],"crucial":[6],"issue":[7],"for":[8],"any":[9],"automatic":[10],"speech":[11,93],"recognition":[12],"(ASR)":[13],"service":[14],"provider":[15],"when":[16],"dealing":[17],"with":[18,50],"clients.":[19,32,83],"In":[20],"this":[21],"paper,":[22],"we":[23],"investigate":[24],"federated":[25,74,105,127,143],"acoustic":[26,100,115,128,144],"modeling":[27,129],"using":[28],"data":[29,35,41,81,94],"from":[30,95],"multiple":[31,96],"A":[33],"client\u2019s":[34],"stored":[37],"on":[38,89],"local":[40],"server":[42],"the":[44,64,69,122,125,139,142],"clients":[45],"communicate":[46],"only":[47],"model":[48,116],"parameters":[49],"central":[52],"server,":[53],"not":[55],"their":[56,108],"data.":[57],"The":[58,84,118],"communication":[59,65],"happens":[60],"infrequently":[61],"to":[62,79,112],"reduce":[63],"cost.":[66],"To":[67],"mitigate":[68],"non-iid":[70],"issue,":[71],"client":[72],"adaptive":[73],"training":[75],"(CAFT)":[76],"proposed":[78,126],"canonicalize":[80],"across":[82],"experiments":[85],"are":[86,102],"carried":[87],"out":[88],"1,150":[90],"hours":[91],"of":[92,124,141],"domains.":[97],"Hybrid":[98],"LSTM":[99],"models":[101],"trained":[103],"via":[104],"learning":[106],"performance":[109,140],"compared":[111],"traditional":[113],"centralized":[114],"training.":[117],"experimental":[119],"results":[120],"demonstrate":[121],"effectiveness":[123],"strategy.":[130],"We":[131],"also":[132],"show":[133],"that":[134],"CAFT":[135],"can":[136],"further":[137],"improve":[138],"model.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3}],"updated_date":"2026-01-23T23:20:30.427331","created_date":"2025-10-10T00:00:00"}