{"id":"https://openalex.org/W4417001731","doi":"https://doi.org/10.1109/lsp.2025.3640524","title":"Comparative Analysis of Automatic Speech Recognition Fine-Tuning Strategies for Speech From Cochlear Implant Users","display_name":"Comparative Analysis of Automatic Speech Recognition Fine-Tuning Strategies for Speech From Cochlear Implant Users","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417001731","doi":"https://doi.org/10.1109/lsp.2025.3640524"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3640524","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3640524","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lsp.2025.3640524","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102675409","display_name":"Seojin Yoon","orcid":"https://orcid.org/0009-0006-7309-5604"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seojin Yoon","raw_affiliation_strings":["Department of Electronic Engineering, Inha University, Incheon, South Korea","Department of Electronic Engineering, Inha University, Incheon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-7309-5604","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Inha University, Incheon, South Korea","institution_ids":["https://openalex.org/I191879574"]},{"raw_affiliation_string":"Department of Electronic Engineering, Inha University, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618302","display_name":"Hyunji Kim","orcid":"https://orcid.org/0000-0002-2066-3843"},"institutions":[{"id":"https://openalex.org/I4210153373","display_name":"Inha University Hospital","ror":"https://ror.org/04gj5px28","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I191879574","https://openalex.org/I4210153373"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunji Kim","raw_affiliation_strings":["Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, South Korea","Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, South Korea","institution_ids":["https://openalex.org/I4210153373"]},{"raw_affiliation_string":"Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I4210153373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101431040","display_name":"Kyu\u2010Sung Kim","orcid":"https://orcid.org/0000-0002-5650-3526"},"institutions":[{"id":"https://openalex.org/I4210153373","display_name":"Inha University Hospital","ror":"https://ror.org/04gj5px28","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I191879574","https://openalex.org/I4210153373"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyusung Kim","raw_affiliation_strings":["Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, South Korea","Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, South Korea","institution_ids":["https://openalex.org/I4210153373"]},{"raw_affiliation_string":"Department of Otorhinolaryngology-HNS Inha University Hospital, Inha University, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I4210153373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100319597","display_name":"Sangmin Lee","orcid":"https://orcid.org/0000-0001-6648-6099"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Lee","raw_affiliation_strings":["Department of Electronic Engineering, Inha University, Incheon, South Korea","Department of Electronic Engineering, Inha University, Incheon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6648-6099","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Inha University, Incheon, South Korea","institution_ids":["https://openalex.org/I191879574"]},{"raw_affiliation_string":"Department of Electronic Engineering, Inha University, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82766635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"33","issue":null,"first_page":"236","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.475600004196167,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.475600004196167,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.38199999928474426,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.07400000095367432,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cochlear-implant","display_name":"Cochlear implant","score":0.7161999940872192},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5236999988555908},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47380000352859497},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4713999927043915},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4431000053882599},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3977000117301941},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3853999972343445},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.34769999980926514}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8007000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587000131607056},{"id":"https://openalex.org/C2778882171","wikidata":"https://www.wikidata.org/wiki/Q724965","display_name":"Cochlear implant","level":2,"score":0.7161999940872192},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4431000053882599},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3853999972343445},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.34769999980926514},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.33719998598098755},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.33000001311302185},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3640524","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3640524","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2025.3640524","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3640524","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2637157702","display_name":null,"funder_award_id":"RS-2024-00348937","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2508158923","https://openalex.org/W2765687795","https://openalex.org/W2938757327","https://openalex.org/W2964525587","https://openalex.org/W4224103177","https://openalex.org/W4372263660","https://openalex.org/W4385245566","https://openalex.org/W4385823097","https://openalex.org/W4386025707","https://openalex.org/W4399334958","https://openalex.org/W4400527802","https://openalex.org/W4401702377","https://openalex.org/W4402112032","https://openalex.org/W4403826739","https://openalex.org/W4405709375"],"related_works":[],"abstract_inverted_index":{"Although":[0],"automatic":[1],"speech":[2,15,53,78],"recognition":[3,54,90],"technology":[4],"has":[5],"become":[6],"widespread,":[7],"it":[8],"still":[9],"exhibits":[10],"limited":[11],"performance":[12,62,91,113,123,136],"when":[13],"processing":[14],"from":[16],"cochlear":[17],"implant":[18],"(CI)":[19],"users.":[20],"This":[21],"limitation":[22],"serves":[23],"as":[24],"a":[25,39,51,115],"barrier":[26],"that":[27,84,128,139,144],"hinders":[28],"CI":[29,57,76,157],"users'":[30,58,158],"accessibility":[31],"to":[32,47,56,93],"digital":[33],"technology.":[34],"To":[35],"address":[36],"this":[37],"issue,":[38],"comparative":[40],"study":[41],"of":[42,63,106,119,156],"fine-tuning":[43,87],"strategies":[44,127],"was":[45],"conducted":[46],"effectively":[48],"adapt":[49],"Whisper,":[50],"general-purpose":[52],"model,":[55],"speech.":[59,159],"Specifically,":[60],"the":[61,86,94,107,111,131,141,145,152],"full":[64],"fine-tuning,":[65,67],"selective":[66],"adapter,":[68],"and":[69,124],"LoRA":[70],"were":[71],"evaluated":[72],"based":[73],"on":[74],"Korean":[75],"user's":[77],"dataset.":[79],"The":[80],"experimental":[81],"results":[82],"showed":[83,134],"all":[85],"approaches":[88],"improved":[89],"compared":[92],"baseline":[95],"Whisper":[96],"model.":[97],"Notably,":[98],"LoRA-encoder":[99],"approach,":[100],"which":[101],"involved":[102],"training":[103],"only":[104,130],"2.15%":[105],"total":[108],"parameters,":[109],"achieved":[110],"best":[112],"with":[114],"character":[116],"error":[117],"rate":[118],"11.57%,":[120],"demonstrating":[121],"superior":[122],"efficiency.":[125],"Furthermore,":[126],"fine-tuned":[129],"encoder":[132],"consistently":[133],"higher":[135],"than":[137],"those":[138],"adjusted":[140],"decoder,":[142],"confirming":[143],"encoder's":[146],"role":[147],"is":[148],"crucial":[149],"in":[150],"modeling":[151],"unique":[153],"acoustic":[154],"characteristics":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-04T00:00:00"}