{"id":"https://openalex.org/W3023953056","doi":"https://doi.org/10.1109/asru51503.2021.9687910","title":"Incremental Learning for End-to-End Automatic Speech Recognition","display_name":"Incremental Learning for End-to-End Automatic Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3023953056","doi":"https://doi.org/10.1109/asru51503.2021.9687910","mag":"3023953056"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687910","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 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/A5101865288","display_name":"Li Fu","orcid":"https://orcid.org/0000-0002-7533-692X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Fu","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458648","display_name":"Xiaoxiao Li","orcid":"https://orcid.org/0000-0002-0376-5135"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Li","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008646809","display_name":"Libo Zi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Zi","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050780","display_name":"Zhengchen Zhang","orcid":"https://orcid.org/0009-0005-4225-3537"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengchen Zhang","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011555779","display_name":"Youzheng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youzheng Wu","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808331","display_name":"Bowen Zhou","orcid":"https://orcid.org/0009-0004-3414-6267"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Zhou","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101865288"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":2.3875,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9098897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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/forgetting","display_name":"Forgetting","score":0.8672052025794983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8501715660095215},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5848631262779236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5555169582366943},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5532846450805664},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.5362303853034973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5231122374534607},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.48654261231422424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45211634039878845},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4491979777812958},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08383437991142273}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8672052025794983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501715660095215},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5848631262779236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5555169582366943},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5532846450805664},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.5362303853034973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5231122374534607},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.48654261231422424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45211634039878845},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4491979777812958},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08383437991142273},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687910","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2026149468","https://openalex.org/W2106433180","https://openalex.org/W2134800885","https://openalex.org/W2193413348","https://openalex.org/W2284628133","https://openalex.org/W2327501763","https://openalex.org/W2473930607","https://openalex.org/W2561238782","https://openalex.org/W2739427748","https://openalex.org/W2750499125","https://openalex.org/W2804175194","https://openalex.org/W2884282566","https://openalex.org/W2889048668","https://openalex.org/W2911291251","https://openalex.org/W2936503027","https://openalex.org/W2954929116","https://openalex.org/W2962858109","https://openalex.org/W2963242190","https://openalex.org/W2963827914","https://openalex.org/W2963850662","https://openalex.org/W2972313371","https://openalex.org/W2972315886","https://openalex.org/W2972389417","https://openalex.org/W2973040747","https://openalex.org/W3006752097","https://openalex.org/W3008876072","https://openalex.org/W3021931813","https://openalex.org/W3030364939","https://openalex.org/W3034368386","https://openalex.org/W3048123939","https://openalex.org/W3091787298","https://openalex.org/W3096626135","https://openalex.org/W3097968133","https://openalex.org/W3138154797","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6679855610","https://openalex.org/W6687566353","https://openalex.org/W6695553435","https://openalex.org/W6730179637","https://openalex.org/W6741807409","https://openalex.org/W6743440867","https://openalex.org/W6751591294","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W3186262193","https://openalex.org/W3192176272","https://openalex.org/W4297634446","https://openalex.org/W4381322349","https://openalex.org/W3157400488","https://openalex.org/W4382021137","https://openalex.org/W3034933965","https://openalex.org/W2892655153","https://openalex.org/W4292793971","https://openalex.org/W4287067590"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,42],"propose":[4],"an":[5,17],"incremental":[6,40],"learning":[7],"method":[8,73,111,135],"for":[9,49,69],"end-to-end":[10],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR)":[14],"which":[15,52,84,142],"enables":[16],"ASR":[18,50],"system":[19],"to":[20,60,77,124],"perform":[21],"well":[22],"on":[23,30,102],"new":[24],"tasks":[25],"while":[26],"maintaining":[27],"the":[28,62,67,70,78,86,89,125,130,147,150],"performance":[29,131],"its":[31],"originally":[32],"learned":[33],"ones.":[34],"To":[35],"mitigate":[36],"catastrophic":[37],"forgetting":[38],"during":[39],"learning,":[41],"design":[43],"a":[44,56,103],"novel":[45],"explainability-based":[46],"knowledge":[47,58],"distillation":[48,59],"models,":[51],"is":[53,92,99,136,143],"combined":[54],"with":[55],"response-based":[57],"maintain":[61],"original":[63,82],"model's":[64],"predictions":[65],"and":[66],"\u201creason\u201d":[68],"predictions.":[71],"Our":[72],"works":[74],"without":[75],"access":[76],"training":[79,98,106,128],"data":[80,91],"of":[81,133,149],"tasks,":[83],"addresses":[85],"cases":[87],"where":[88],"previous":[90],"no":[93],"longer":[94],"available":[95],"or":[96],"joint":[97,127],"costly.":[100],"Results":[101],"multi-stage":[104],"sequential":[105],"task":[107],"show":[108],"that":[109],"our":[110,134],"outperforms":[112],"existing":[113],"ones":[114],"in":[115,119],"mitigating":[116],"forgetting.":[117],"Furthermore,":[118],"two":[120],"practical":[121],"scenarios,":[122],"compared":[123],"target-reference":[126],"method,":[129],"drop":[132],"0.02%":[137],"Character":[138],"Error":[139],"Rate":[140],"(CER),":[141],"97%":[144],"smaller":[145],"than":[146],"drops":[148],"baseline":[151],"methods.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}