{"id":"https://openalex.org/W4405633169","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800352","title":"Continual Learning in Machine Speech Chain Using Gradient Episodic Memory","display_name":"Continual Learning in Machine Speech Chain Using Gradient Episodic Memory","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633169","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800352"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5114988709","display_name":"Geoffrey Tyndall","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Geoffrey Tyndall","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115563156","display_name":"Kurniawati Arizah","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Arizah","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066930701","display_name":"Dipta Tanaya","orcid":"https://orcid.org/0009-0000-1480-8041"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dipta Tanaya","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021128017","display_name":"Ayu Purwarianti","orcid":"https://orcid.org/0000-0002-5016-3700"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ayu Purwarianti","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Puji Lestari","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114988709"],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78005307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9362999796867371,"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":0.9362999796867371,"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/computer-science","display_name":"Computer science","score":0.7269791960716248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5112495422363281},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.5012168884277344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4529893696308136},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3515551686286926},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14225664734840393},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.0989728569984436},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.09495630860328674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269791960716248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5112495422363281},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.5012168884277344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4529893696308136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3515551686286926},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14225664734840393},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.0989728569984436},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.09495630860328674}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W2407386500","https://openalex.org/W2560647685","https://openalex.org/W2892009249","https://openalex.org/W2903739847","https://openalex.org/W3009565979","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W4289913100","https://openalex.org/W6738602802","https://openalex.org/W6739901393","https://openalex.org/W6741087337","https://openalex.org/W6741217325","https://openalex.org/W6748367459","https://openalex.org/W6761449031","https://openalex.org/W6847363464","https://openalex.org/W6848676343"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Continual":[0],"learning":[1,41,101,133],"for":[2,66,128],"automatic":[3],"speech":[4,35,58,125,135],"recognition":[5],"(ASR)":[6],"systems":[7],"poses":[8],"a":[9,29,51,104],"challenge,":[10],"especially":[11],"with":[12],"the":[13,33,56,62,69,88,119],"need":[14],"to":[15,38,72],"avoid":[16],"catastrophic":[17],"forgetting":[18],"while":[19,109],"maintaining":[20,110],"performance":[21,79,112],"on":[22,81,87],"previously":[23],"learned":[24],"tasks.":[25,83],"This":[26],"paper":[27],"introduces":[28],"novel":[30],"approach":[31,127],"leveraging":[32],"machine":[34,57,124],"chain":[36,126],"framework":[37],"enable":[39],"continual":[40,132],"in":[42,134],"ASR":[43,70],"using":[44],"gradient":[45],"episodic":[46],"memory":[47],"(GEM).":[48],"By":[49],"incorporating":[50],"text-to-speech":[52],"(TTS)":[53],"component":[54],"within":[55],"chain,":[59],"we":[60],"support":[61],"replay":[63],"mechanism":[64],"essential":[65],"GEM,":[67],"allowing":[68],"model":[71],"learn":[73],"new":[74],"tasks":[75],"sequentially":[76],"without":[77],"significant":[78],"degradation":[80],"earlier":[82],"Our":[84],"experiments,":[85],"conducted":[86],"LJ":[89],"Speech":[90],"dataset,":[91],"demonstrate":[92],"that":[93],"our":[94,122],"method":[95],"outperforms":[96],"traditional":[97],"fine-tuning":[98],"and":[99,130],"multitask":[100],"approaches,":[102],"achieving":[103],"substantial":[105],"error":[106],"rate":[107],"reduction":[108],"high":[111],"across":[113],"varying":[114],"noise":[115],"conditions.":[116],"We":[117],"showed":[118],"potential":[120],"of":[121],"semi-supervised":[123],"effective":[129],"efficient":[131],"recognition.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
