{"id":"https://openalex.org/W4375868783","doi":"https://doi.org/10.1109/icassp49357.2023.10095484","title":"Continual Learning for On-Device Speech Recognition Using Disentangled Conformers","display_name":"Continual Learning for On-Device Speech Recognition Using Disentangled Conformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868783","doi":"https://doi.org/10.1109/icassp49357.2023.10095484"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5016426491","display_name":"Anuj Diwan","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuj Diwan","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ching-Feng Yeh","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027043104","display_name":"Paden Tomasello","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paden Tomasello","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035142405","display_name":"Eunsol Choi","orcid":"https://orcid.org/0000-0003-3607-9104"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eunsol Choi","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101170706","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3067,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81707219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9959999918937683,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9876999855041504,"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":0.9460999965667725,"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":0.848310112953186},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7309402227401733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5933398604393005},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5057358741760254},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47170567512512207},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.468264639377594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45602506399154663},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4145069718360901},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3828796148300171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848310112953186},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7309402227401733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5933398604393005},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5057358741760254},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47170567512512207},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.468264639377594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45602506399154663},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4145069718360901},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3828796148300171},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1682403713","https://openalex.org/W2127141656","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2593463961","https://openalex.org/W2612690371","https://openalex.org/W2913668833","https://openalex.org/W2939911019","https://openalex.org/W2962760690","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3097968133","https://openalex.org/W3198094329","https://openalex.org/W3202725408","https://openalex.org/W3207326706","https://openalex.org/W4224821750","https://openalex.org/W4224930323","https://openalex.org/W4296070390","https://openalex.org/W4312789614","https://openalex.org/W6741087337","https://openalex.org/W6759579507","https://openalex.org/W6762042405","https://openalex.org/W6771812881","https://openalex.org/W6780218876","https://openalex.org/W6803315452"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,14,66],"recognition":[2,67],"research":[3],"focuses":[4],"on":[5,9,19,144,152,166],"training":[6,83],"and":[7,55,69,88,113,168],"evaluating":[8],"static":[10],"datasets.":[11],"Yet,":[12],"as":[13],"models":[15,23,68,103,140],"are":[16,73],"increasingly":[17],"deployed":[18],"personal":[20],"devices,":[21],"such":[22,122],"encounter":[24],"user-specific":[25],"distributional":[26],"shifts.":[27],"To":[28],"simulate":[29],"this":[30],"real-world":[31],"scenario,":[32],"we":[33,124],"introduce":[34],"LibriContinual,":[35],"a":[36,81,90,106,126],"continual":[37,70,129],"learning":[38,71,130],"benchmark":[39],"for":[40,86,110,118],"speaker-specific":[41,119,155],"domain":[42],"adaptation":[43],"derived":[44],"from":[45],"LibriVox":[46],"audiobooks,":[47],"with":[48],"data":[49],"corresponding":[50],"to":[51,76],"118":[52],"individual":[53],"speakers":[54],"6":[56],"train":[57],"splits":[58],"per":[59],"speaker":[60],"of":[61,105],"different":[62],"sizes.":[63],"Additionally,":[64],"current":[65],"algorithms":[72],"not":[74],"optimized":[75],"be":[77],"compute-efficient.":[78],"We":[79],"adapt":[80],"general-purpose":[82,111],"algorithm":[84,100,131],"NetAug":[85],"ASR":[87,102,146],"create":[89],"novel":[91,127],"Conformer":[92],"variant":[93],"called":[94,132],"the":[95,138],"DisConformer":[96,139],"(Disentangled":[97],"Conformer).":[98],"This":[99],"produces":[101],"consisting":[104],"frozen":[107],"\u2018core\u2019":[108],"network":[109],"use":[112],"several":[114],"tunable":[115],"\u2018augment\u2019":[116],"networks":[117],"tuning.":[120],"Using":[121],"models,":[123],"propose":[125],"compute-efficient":[128],"DisentangledCL.":[133],"Our":[134],"experiments":[135],"show":[136],"that":[137],"significantly":[141,158],"outperform":[142],"base-lines":[143],"general":[145],"i.e.":[147],"LibriSpeech":[148],"(15.58%":[149],"rel.":[150,164],"WER":[151,165],"test-other).":[153],"On":[154],"LibriContinual":[156],"they":[157],"outper-form":[159],"trainable-parameter-matched":[160],"baselines":[161,173],"(by":[162],"20.65%":[163],"test)":[167],"even":[169],"match":[170],"fully":[171],"finetuned":[172],"in":[174],"some":[175],"settings.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-05-10T00:00:00"}