{"id":"https://openalex.org/W4283814447","doi":"https://doi.org/10.21437/interspeech.2022-11282","title":"Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models","display_name":"Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283814447","doi":"https://doi.org/10.21437/interspeech.2022-11282"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11282","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11282","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5087545401","display_name":"Yuki Takashima","orcid":"https://orcid.org/0000-0001-8489-9487"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Takashima","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, USA","Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia Perera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052394367","display_name":"Yohei Kawaguchi","orcid":"https://orcid.org/0000-0002-2329-5441"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Kawaguchi","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087545401"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52476281,"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":"2218","last_page":"2222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9830999970436096,"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":0.9810000061988831,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8017218708992004},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7837051749229431},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6894022226333618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6498206257820129},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34206998348236084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24356141686439514},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07175630331039429},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.06560838222503662}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8017218708992004},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7837051749229431},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6894022226333618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498206257820129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34206998348236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24356141686439514},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07175630331039429},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.06560838222503662},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11282","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11282","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions"}],"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/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2125336414","https://openalex.org/W2131953535","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2748545504","https://openalex.org/W2788388592","https://openalex.org/W2889074736","https://openalex.org/W2962780374","https://openalex.org/W2963540014","https://openalex.org/W2963979492","https://openalex.org/W2972818416","https://openalex.org/W3008876072","https://openalex.org/W3023953056","https://openalex.org/W3095783102","https://openalex.org/W3097777922","https://openalex.org/W3097968133","https://openalex.org/W3170463198","https://openalex.org/W3212574065","https://openalex.org/W4225295099","https://openalex.org/W4295883599","https://openalex.org/W4319862695","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W3183027292","https://openalex.org/W4310285384","https://openalex.org/W2794885965"],"abstract_inverted_index":{"In":[0],"this":[1,56,119],"paper,":[2],"we":[3,58,121],"present":[4],"an":[5,15,123],"incremental":[6,82],"domain":[7,74,83],"adaptation":[8,84],"technique":[9],"to":[10,39,43,68,89,131,149],"prevent":[11,112],"catastrophic":[12,77,113,146],"forgetting":[13,147],"for":[14,33],"end-to-end":[16,44,64,97],"automatic":[17],"speech":[18],"recognition":[19],"(ASR)":[20],"model.Conventional":[21],"approaches":[22,42],"require":[23],"extra":[24],"parameters":[25],"of":[26,53,63,108,118,136],"the":[27,31,72,86,90,105,116,134,153],"same":[28],"size":[29],"as":[30],"model":[32],"optimization,":[34],"and":[35,100],"it":[36],"is":[37],"difficult":[38],"apply":[40],"these":[41],"ASR":[45,65,98],"models":[46,66,99],"because":[47],"they":[48],"have":[49],"a":[50],"huge":[51],"amount":[52],"parameters.To":[54],"solve":[55],"problem,":[57],"first":[59],"investigate":[60],"which":[61],"parts":[62],"contribute":[67],"high":[69],"accuracy":[70],"in":[71],"target":[73],"while":[75],"preventing":[76],"forgetting.We":[78],"conduct":[79],"experiments":[80],"on":[81,115,128],"from":[85,152],"LibriSpeech":[87],"dataset":[88],"AMI":[91],"meeting":[92],"corpus":[93],"with":[94],"two":[95],"popular":[96],"found":[101],"that":[102,141],"adapting":[103],"only":[104],"linear":[106],"layers":[107,130],"their":[109],"encoders":[110],"can":[111],"forgetting.Then,":[114],"basis":[117],"finding,":[120],"develop":[122],"element-wise":[124],"parameter":[125,150],"selection":[126,151],"focused":[127],"specific":[129],"further":[132],"reduce":[133],"number":[135],"fine-tuning":[137],"parameters.Experimental":[138],"results":[139],"show":[140],"our":[142],"approach":[143],"consistently":[144],"prevents":[145],"compared":[148],"whole":[154],"model.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
