{"id":"https://openalex.org/W4416799315","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249418","title":"Few-Shot Speaker Adaptation for Text-to-Speech Synthesis Using Non-Target Speaker Corpora for Glossectomy Patients","display_name":"Few-Shot Speaker Adaptation for Text-to-Speech Synthesis Using Non-Target Speaker Corpora for Glossectomy Patients","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799315","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249418"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249418","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":null,"display_name":"Masayori Okamura","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayori Okamura","raw_affiliation_strings":["Okayama University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Okayama University,Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086032519","display_name":"Masanobu Abe","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanobu Abe","raw_affiliation_strings":["Okayama University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Okayama University,Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070197974","display_name":"Sunao Hara","orcid":"https://orcid.org/0000-0001-5972-5178"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sunao Hara","raw_affiliation_strings":["Okayama University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Okayama University,Japan","institution_ids":["https://openalex.org/I163770644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I163770644"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41096465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1122","last_page":"1127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.6085000038146973,"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":0.6085000038146973,"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":0.08900000154972076,"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/T11374","display_name":"Cleft Lip and Palate Research","score":0.056299999356269836,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7595999836921692},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44589999318122864},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42309999465942383},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4133000075817108},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3869999945163727},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35040000081062317},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.34220001101493835}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7595999836921692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7301999926567078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740000247955322},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42309999465942383},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249418","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2749262635","https://openalex.org/W2888784223","https://openalex.org/W3012235149","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3209059054","https://openalex.org/W4385478010","https://openalex.org/W4406417959"],"related_works":[],"abstract_inverted_index":{"For":[0],"individuals":[1],"with":[2],"articulation":[3],"disorders,":[4],"such":[5],"as":[6],"patients":[7],"after":[8],"subtotal":[9],"glossectomy,":[10],"text-to-speech":[11],"(TTS)":[12],"provides":[13],"a":[14,42,62,91,174],"means":[15],"of":[16,72,94,117,133,163,173],"voice":[17],"communication.":[18],"To":[19,56],"preserve":[20],"personal":[21],"identity":[22,47],"in":[23,153],"TTS,":[24],"speaker":[25,63,109,160,164],"adaptation":[26,64,82],"methods":[27],"are":[28,112,209],"employed.":[29],"However,":[30],"when":[31],"the":[32,45,73,86,105,115,118,125,130,138,154,171,187],"target's":[33,87],"disordered":[34,76,88,97,179,201],"speech":[35,51,89,98,135,180,196,202],"is":[36,41,190],"used":[37],"for":[38,159,192],"adaptation,":[39],"there":[40],"trade-off:":[43],"while":[44],"speaker's":[46,75,176],"can":[48],"be":[49],"reproduced,":[50],"intelligibility":[52,116,141],"tends":[53],"to":[54,107,114,137,144],"deteriorate.":[55],"address":[57],"this":[58],"challenge,":[59],"we":[60],"propose":[61],"method":[65,80,127,169,189],"that":[66,111,124,167,186],"uses":[67],"less":[68],"than":[69],"one":[70],"minute":[71],"target":[74],"speech.":[77,120,146],"The":[78],"proposed":[79,126,188],"performs":[81],"using":[83],"not":[84],"only":[85],"but":[90],"parallel":[92],"corpus":[93],"healthy":[95,145,177],"and":[96,178,200],"from":[99,198],"non-target":[100],"speakers.":[101],"This":[102],"approach":[103],"enables":[104],"model":[106],"learn":[108],"features":[110],"robust":[113],"reference":[119],"Evaluation":[121],"results":[122],"show":[123],"significantly":[128],"improves":[129],"character":[131],"accuracy":[132],"synthesized":[134],"compared":[136],"baseline,":[139],"achieving":[140,193],"levels":[142],"comparable":[143],"Furthermore,":[147],"subjective":[148],"evaluations":[149],"demonstrate":[150,185],"an":[151],"improvement":[152],"mean":[155],"opinion":[156],"score":[157],"(MOS)":[158],"similarity.":[161],"Visualization":[162],"embeddings":[165],"confirmed":[166],"our":[168],"brings":[170],"distributions":[172],"single":[175],"closer":[181],"together.":[182],"These":[183],"findings":[184],"effective":[191],"high-quality,":[194],"personalized":[195],"synthesis":[197],"limited":[199],"samples<sup":[203],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[204,206],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[205],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Audio":[207],"samples":[208],"available":[210],"at":[211],"https://yori2000.github.io/APSIPA-demo/.":[212]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}