{"id":"https://openalex.org/W4416799545","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248972","title":"Improving Automatic Speech Recognition Model for Super-Elderly Voice Using Speech Synthesis Model","display_name":"Improving Automatic Speech Recognition Model for Super-Elderly Voice Using Speech Synthesis Model","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799545","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248972"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5008446767","display_name":"Ryota Uematsu","orcid":null},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Uematsu","raw_affiliation_strings":["University of Yamanashi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Yamanashi,Japan","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070048885","display_name":"Chee Siang Leow","orcid":null},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chee Siang Leow","raw_affiliation_strings":["University of Yamanashi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Yamanashi,Japan","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077234015","display_name":"Norihide Kitaoka","orcid":"https://orcid.org/0000-0003-2028-8585"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihide Kitaoka","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014342555","display_name":"Hiromitsu Nishizaki","orcid":"https://orcid.org/0000-0002-7717-8312"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiromitsu Nishizaki","raw_affiliation_strings":["University of Yamanashi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Yamanashi,Japan","institution_ids":["https://openalex.org/I66906201"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17655163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"986","last_page":"991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8327999711036682,"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":0.8327999711036682,"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/T10863","display_name":"Voice and Speech Disorders","score":0.05400000140070915,"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/T11448","display_name":"Face recognition and analysis","score":0.0142000000923872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/acoustic-model","display_name":"Acoustic model","score":0.5354999899864197},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5159000158309937},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4767000079154968},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47189998626708984},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44600000977516174},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.38580000400543213},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.3824000060558319},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7767000198364258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544999718666077},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5354999899864197},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47189998626708984},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4383000135421753},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.38580000400543213},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.3328999876976013},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2752000093460083}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1697117990","display_name":null,"funder_award_id":"JP23H00493,JP25H00566","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2005522781","https://openalex.org/W2150769028","https://openalex.org/W2890964092","https://openalex.org/W2937579788","https://openalex.org/W2963609956","https://openalex.org/W2972909277","https://openalex.org/W2973142754","https://openalex.org/W3009565979","https://openalex.org/W3162577635","https://openalex.org/W4224012494","https://openalex.org/W4224930731","https://openalex.org/W4254312214","https://openalex.org/W4283452649","https://openalex.org/W4319586244","https://openalex.org/W4385823163","https://openalex.org/W4387682382","https://openalex.org/W4400275735","https://openalex.org/W4402111804","https://openalex.org/W4404609355"],"related_works":[],"abstract_inverted_index":{"Although":[0],"speech":[1,10,49],"recognition":[2,77],"technology":[3],"has":[4],"made":[5],"remarkable":[6],"progress,":[7],"recognizing":[8],"elderly":[9,37,48,59],"remains":[11],"challenging":[12],"due":[13],"to":[14,43,90],"age-related":[15],"acoustic":[16],"characteristics":[17],"and":[18,51],"limited":[19],"training":[20,54],"data.":[21],"This":[22],"paper":[23],"introduces":[24],"a":[25,46,72],"novel":[26],"data":[27,55],"augmentation":[28],"framework":[29],"that":[30,68],"utilizes":[31],"text-to-speech":[32],"synthesis":[33],"specifically":[34],"optimized":[35],"for":[36],"voices.":[38],"Our":[39],"approach":[40],"employs":[41],"Style-BertVITS2":[42],"learn":[44],"from":[45],"small":[47],"corpus":[50,66],"generate":[52],"additional":[53],"while":[56],"preserving":[57],"distinctive":[58],"voice":[60],"characteristics.":[61],"Experiments":[62],"using":[63],"the":[64,80],"EARS":[65],"demonstrate":[67],"our":[69],"method":[70],"achieves":[71],"statistically":[73],"significant":[74],"improvement":[75],"in":[76],"accuracy,":[78],"reducing":[79],"Character":[81],"Error":[82],"Rate":[83],"(CER)":[84],"by":[85],"0.31":[86],"percentage":[87],"points":[88],"compared":[89],"conventional":[91],"approaches.":[92]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}