{"id":"https://openalex.org/W7130376728","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385248","title":"Tuning Tone With Age: Adapting Dialogue Response Generation Based on Llms and Self-Supervised Speaker Age Estimation","display_name":"Tuning Tone With Age: Adapting Dialogue Response Generation Based on Llms and Self-Supervised Speaker Age Estimation","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130376728","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385248"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126348549","display_name":"Riichi Yagi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160746","display_name":"Toho Gakuen","ror":"https://ror.org/05dxj6c66","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210160746"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Riichi Yagi","raw_affiliation_strings":["Tōdaiji Gakuen High School,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tōdaiji Gakuen High School,Japan","institution_ids":["https://openalex.org/I4210160746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126292799","display_name":"Wangzixi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wangzixi Zhou","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126343003","display_name":"Hongwei Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hongwei Hu","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126329700","display_name":"Yuta Hirano","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Hirano","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.24480000138282776,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.24480000138282776,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.1785999983549118,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.1354999989271164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/casual","display_name":"Casual","score":0.7124999761581421},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7057999968528748},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6122999787330627},{"id":"https://openalex.org/keywords/politeness","display_name":"Politeness","score":0.536300003528595},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4235000014305115},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41510000824928284},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C2781426162","wikidata":"https://www.wikidata.org/wiki/Q2275793","display_name":"Casual","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7057999968528748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6596999764442444},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6122999787330627},{"id":"https://openalex.org/C61123122","wikidata":"https://www.wikidata.org/wiki/Q281287","display_name":"Politeness","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.35589998960494995},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34950000047683716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6134353280067444,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1681725068","https://openalex.org/W2791762836","https://openalex.org/W3160812582","https://openalex.org/W3181310845","https://openalex.org/W3196475561","https://openalex.org/W3208743843","https://openalex.org/W3209984917","https://openalex.org/W4226170304","https://openalex.org/W4290742115","https://openalex.org/W4313639694","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"speech":[1,80],"dialogue":[2,54],"systems":[3],"often":[4],"default":[5],"to":[6],"polite":[7],"language.":[8],"While":[9],"this":[10],"minimizes":[11],"discomfort,":[12],"it":[13],"can":[14],"create":[15],"psychological":[16],"distance":[17],"by":[18,117],"ignoring":[19],"user":[20],"attributes":[21],"such":[22],"as":[23,139],"age":[24,76,97,114],"and":[25,88,137],"gender.":[26],"Such":[27],"a":[28,42,72,83,104],"one-size-fits-all":[29],"approach":[30],"risks":[31],"producing":[32],"unnatural":[33],"interactions,":[34],"especially":[35],"for":[36],"younger":[37],"users":[38],"who":[39],"may":[40],"prefer":[41],"more":[43],"casual":[44],"tone.":[45],"To":[46],"address":[47],"this,":[48],"we":[49],"propose":[50],"an":[51],"age-aware":[52],"spoken":[53],"system":[55,67],"that":[56],"adapts":[57],"conversational":[58],"style":[59],"based":[60],"on":[61],"the":[62,120,126],"speaker's":[63],"estimated":[64],"age.":[65],"The":[66,92],"integrates":[68],"four":[69],"core":[70],"components:":[71],"self-supervised":[73],"learning":[74],"(SSL)-based":[75],"estimation":[77],"model,":[78],"automatic":[79],"recognition":[81],"(ASR),":[82],"large":[84],"language":[85],"model":[86,94],"(LLM),":[87],"text-to-speech":[89],"(TTS)":[90],"synthesis.":[91],"SSL-based":[93],"predicts":[95],"speaker":[96],"from":[98],"voice":[99],"with":[100],"higher":[101],"accuracy":[102],"than":[103],"conventional":[105],"Fbank-based":[106],"baseline,":[107],"achieving":[108],"lower":[109],"mean":[110,143],"absolute":[111],"error":[112],"across":[113],"groups.":[115],"Guided":[116],"these":[118],"predictions,":[119],"LLM":[121],"adjusts":[122],"tone":[123],"dynamically,":[124],"while":[125],"TTS":[127],"module":[128],"generates":[129],"age-appropriate":[130],"voices.":[131],"Experimental":[132],"results":[133],"confirm":[134],"improved":[135],"naturalness":[136],"expressiveness,":[138],"verified":[140],"through":[141],"machine":[142],"opinion":[144],"scores":[145],"(MOS).":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}