{"id":"https://openalex.org/W7125956025","doi":"https://doi.org/10.1109/smc58881.2025.11342780","title":"A Dysarthric Speech Recognition System with Personal Style Embedding","display_name":"A Dysarthric Speech Recognition System with Personal Style Embedding","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125956025","doi":"https://doi.org/10.1109/smc58881.2025.11342780"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5101996635","display_name":"Yu-Chen Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I99613584","display_name":"National Taipei University","ror":"https://ror.org/03e29r284","country_code":"TW","type":"education","lineage":["https://openalex.org/I99613584"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Chen Hsu","raw_affiliation_strings":["National Taipei University,New Taipei City,Taiwan, R.O.C.,237303"],"affiliations":[{"raw_affiliation_string":"National Taipei University,New Taipei City,Taiwan, R.O.C.,237303","institution_ids":["https://openalex.org/I99613584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091227387","display_name":"Y. A. Chang","orcid":"https://orcid.org/0000-0002-0997-4069"},"institutions":[{"id":"https://openalex.org/I99613584","display_name":"National Taipei University","ror":"https://ror.org/03e29r284","country_code":"TW","type":"education","lineage":["https://openalex.org/I99613584"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yue-Shan Chang","raw_affiliation_strings":["National Taipei University,New Taipei City,Taiwan, R.O.C.,237303"],"affiliations":[{"raw_affiliation_string":"National Taipei University,New Taipei City,Taiwan, R.O.C.,237303","institution_ids":["https://openalex.org/I99613584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101996635"],"corresponding_institution_ids":["https://openalex.org/I99613584"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71255468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3770","last_page":"3775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.004900000058114529,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6182000041007996},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5221999883651733},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4462999999523163},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4323999881744385},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4034000039100647},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.387800008058548},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.36980000138282776},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.36320000886917114},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3467999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609999775886536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7437000274658203},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4462999999523163},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4034000039100647},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41341039538383484,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2910712032","https://openalex.org/W4385245566","https://openalex.org/W4385822407","https://openalex.org/W4403210835","https://openalex.org/W4405709358"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"automatic":[1,154],"speech":[2,11,45,102,134,155,183],"recognition":[3,146,156],"(ASR)":[4,157],"systems":[5],"often":[6],"encounter":[7],"difficulties":[8],"in":[9,145,168],"processing":[10,43,149],"of":[12,46,54,92,164],"dysarthric":[13],"people,":[14],"which":[15,88],"is":[16,81],"characterized":[17],"by":[18,70],"impaired":[19],"neuromuscular":[20],"control":[21],"and":[22,34,75,107,148],"atypical":[23],"articulation.":[24],"Existing":[25],"commercial":[26],"solutions,":[27],"such":[28],"as":[29],"Google":[30],"Speech":[31],"to":[32,66,99,132,152],"Text":[33],"Microsoft":[35],"Azure":[36],"Speech,":[37],"exhibit":[38],"high":[39],"error":[40],"rates":[41],"when":[42],"the":[44,52,84,90,93,121,140,162],"people":[47,181],"with":[48,182],"dysarthria,":[49],"severely":[50],"hindering":[51],"accessibility":[53],"communication.":[55],"This":[56,159],"study":[57],"introduces":[58],"a":[59,109,124,173],"novel":[60],"personalized":[61,125],"ASR":[62],"system":[63,80,122,141],"that":[64,128,139],"aims":[65],"address":[67],"these":[68],"challenges":[69],"integrating":[71],"speaker":[72],"adaptive":[73],"modeling":[74],"advanced":[76],"correction":[77,112,126],"mechanisms.":[78],"The":[79],"based":[82],"on":[83],"transformer-based":[85,94],"SenseVoice":[86],"mini-model,":[87],"utilizes":[89],"functionality":[91],"Large":[95],"Language":[96],"Model":[97],"(LLM)":[98],"extract":[100],"speaker-specific":[101],"features":[103],"from":[104],"historical":[105],"data":[106],"implement":[108],"dynamic":[110],"history":[111],"algorithm.":[113],"By":[114],"employing":[115],"an":[116],"LLM-based":[117],"style":[118],"extraction":[119],"method,":[120],"develops":[123],"model":[127],"can":[129],"be":[130],"adapted":[131],"individual":[133],"variations.":[135],"Experimental":[136],"evaluations":[137],"show":[138],"provides":[142],"substantial":[143],"improvements":[144],"accuracy":[147],"efficiency":[150],"compared":[151],"traditional":[153],"techniques.":[158],"research":[160],"highlights":[161],"potential":[163],"AI-driven":[165],"personalization":[166],"approaches":[167],"assistive":[169],"communication":[170,178],"technologies,":[171],"providing":[172],"promising":[174],"avenue":[175],"for":[176,180],"enhancing":[177],"tools":[179],"impairments.":[184]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}