{"id":"https://openalex.org/W4313306162","doi":"https://doi.org/10.1109/taslp.2022.3233238","title":"Domain Expansion for End-to-End Speech Recognition: Applications for Accent/Dialect Speech","display_name":"Domain Expansion for End-to-End Speech Recognition: Applications for Accent/Dialect Speech","publication_year":2022,"publication_date":"2022-12-30","ids":{"openalex":"https://openalex.org/W4313306162","doi":"https://doi.org/10.1109/taslp.2022.3233238"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3233238","doi":"https://doi.org/10.1109/taslp.2022.3233238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3233238","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/A5075220607","display_name":"Shahram Ghorbani","orcid":"https://orcid.org/0000-0002-8118-5515","observed_orcids":["https://orcid.org/0000-0002-8118-5515"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahram Ghorbani","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-8118-5515","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":0.9047,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75054116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"762","last_page":"774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9746000170707703,"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":0.9746000170707703,"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":0.024299999698996544,"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":0.00019999999494757503,"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/domain-expansion","display_name":"domain expansion","score":0.7599999904632568},{"id":"https://openalex.org/keywords/catastrophic-forgetting","display_name":"catastrophic forgetting","score":0.8569999933242798},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.7110000252723694},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"end-to-end speech recognition","score":0.8479999899864197},{"id":"https://openalex.org/keywords/accent-adaptation","display_name":"accent adaptation","score":0.7599999904632568},{"id":"https://openalex.org/keywords/dialectal-speech","display_name":"dialect speech","score":0.921999990940094},{"id":"https://openalex.org/keywords/model-averaging","display_name":"model averaging","score":0.5910000205039978},{"id":"https://openalex.org/keywords/gradient-averaging","display_name":"gradient averaging","score":0.6980000138282776},{"id":"https://openalex.org/keywords/kl-divergence-regularization","display_name":"KL divergence regularization","score":0.7789999842643738},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"episodic memory","score":0.6420000195503235},{"id":"https://openalex.org/keywords/reskilling","display_name":"retraining","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519692182540894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6418960094451904},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6275935173034668},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6072402000427246},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5459108352661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44458407163619995},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4272025525569916},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.41347530484199524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36260634660720825},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.19795304536819458},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3233238","doi":"https://doi.org/10.1109/taslp.2022.3233238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3233238","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1989549063","https://openalex.org/W2062164080","https://openalex.org/W2079735306","https://openalex.org/W2127141656","https://openalex.org/W2162042984","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2587088898","https://openalex.org/W2604763608","https://openalex.org/W2605043629","https://openalex.org/W2734314755","https://openalex.org/W2737492962","https://openalex.org/W2809425026","https://openalex.org/W2886246524","https://openalex.org/W2889488531","https://openalex.org/W2889785444","https://openalex.org/W2902625698","https://openalex.org/W2963178577","https://openalex.org/W2963211739","https://openalex.org/W2968596670","https://openalex.org/W2970971581","https://openalex.org/W2978556807","https://openalex.org/W2980753060","https://openalex.org/W3008008574","https://openalex.org/W3091787298","https://openalex.org/W3093579165","https://openalex.org/W3097968133","https://openalex.org/W3102438316","https://openalex.org/W3104773308","https://openalex.org/W3112702554","https://openalex.org/W3136989387","https://openalex.org/W3156258992","https://openalex.org/W3160525311","https://openalex.org/W3162061711","https://openalex.org/W3163842339","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W2978556807","https://openalex.org/W3025521026","https://openalex.org/W3207572704","https://openalex.org/W4375869215","https://openalex.org/W2886246524","https://openalex.org/W4319862655","https://openalex.org/W4385261418","https://openalex.org/W4372347360","https://openalex.org/W4404782863","https://openalex.org/W4319586290"],"abstract_inverted_index":{"Training":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"with":[6,95],"sequentially":[7],"incoming":[8],"data":[9,67,78,179],"from":[10],"alternate":[11],"domains":[12,157],"is":[13,33,68],"an":[14,194],"essential":[15],"milestone":[16],"in":[17,24,39],"order":[18],"to":[19,98,114,180],"reach":[20],"human":[21],"intelligibility":[22],"level":[23],"speech":[25],"recognition.":[26],"The":[27,121],"main":[28],"challenge":[29],"of":[30,85,118,127,161],"sequential":[31],"learning":[32,218],"that":[34,210],"current":[35],"adaptation":[36],"techniques":[37,58],"result":[38],"significant":[40],"performance":[41,116,126],"degradation":[42],"for":[43,59,202],"previously-seen":[44],"domains.":[45,207],"To":[46],"mitigate":[47,115],"the":[48,83,86,103,124,142,150,155,162,168,182,234],"catastrophic":[49],"forgetting":[50,143],"problem,":[51],"this":[52,137],"study":[53,107],"proposes":[54],"effective":[55],"domain":[56,66,77],"expansion":[57],"two":[60,156],"scenarios:":[61],"1)":[62],"where":[63,72],"only":[64],"new":[65,76,206],"available,":[69],"and":[70,75,110,164,205,214],"2)":[71],"both":[73,203],"prior":[74],"are":[79],"available.":[80],"We":[81,186],"examine":[82],"efficacy":[84],"approaches":[87,113],"through":[88],"experiments":[89,122],"on":[90],"adapting":[91],"a":[92],"model":[93,184],"trained":[94],"native":[96],"English":[97,100],"different":[99],"accents.":[101],"For":[102,167],"first":[104,140],"scenario,":[105,170],"we":[106,171],"several":[108,173],"existing":[109],"proposed":[111,129],"regularization-based":[112],"loss":[117],"initial":[119,163,178,204],"data.":[120],"demonstrate":[123,209],"superior":[125],"our":[128],"Soft":[130],"KL-Divergence":[131],"(SKLD)-Model":[132],"Averaging":[133,189],"(MA)":[134],"approach.":[135,237],"In":[136],"approach,":[138],"SKLD":[139],"alleviates":[141],"problem":[144],"during":[145],"adaptation;":[146],"next,":[147],"MA":[148],"makes":[149],"final":[151],"efficient":[152],"compromise":[153],"between":[154],"by":[158,198],"averaging":[159,199],"parameters":[160],"adapted":[165],"models.":[166],"second":[169],"explore":[172],"rehearsal-based":[174],"approaches,":[175,219],"which":[176,196],"leverage":[177],"maintain":[181],"original":[183],"performance.":[185],"propose":[187],"Gradient":[188,223],"(GA)":[190],"as":[191,193,221],"well":[192],"approach":[195],"operates":[197],"gradients":[200],"computed":[201],"Experiments":[208],"GA":[211,228],"outperforms":[212],"retraining":[213,236],"specifically":[215],"designed":[216],"continual":[217],"such":[220],"Averaged":[222],"Episodic":[224],"Memory":[225],"(AGEM).":[226],"Moreover,":[227],"significantly":[229],"improves":[230],"computational":[231],"costs":[232],"over":[233],"complete":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-01-06T00:00:00"}