{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T07:19:58Z","timestamp":1771485598874,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1109\/o-cocosda68185.2025.11385248","type":"proceedings-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:14:09Z","timestamp":1771449249000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Tuning Tone With Age: Adapting Dialogue Response Generation Based on Llms and Self-Supervised Speaker Age Estimation"],"prefix":"10.1109","author":[{"given":"Riichi","family":"Yagi","sequence":"first","affiliation":[{"name":"Tōdaiji Gakuen High School,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangzixi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Hu","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuta","family":"Hirano","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"History of generative arti-ficial intelligence (ai) chatbots: past, present, and future development","author":"Md Al-Amin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3166054.3166058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0278323"},{"key":"ref4","first-page":"30","article-title":"Should speech dialogue system use honorific expression?comparative study on understanding impressions of different politeness utterances","volume-title":"Human-Agent Interaction Symposium","author":"Ouchi"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.029"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-440"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2816163"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s21144785"},{"key":"ref9","article-title":"S3prl: The selfsupervised speech pre-training and representation learning toolkit","volume-title":"online GitHub repository","author":"T Liu","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414272"},{"key":"ref11","article-title":"Voxceleb 2: Deep speaker recognition","author":"Son Chung","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"8024","article-title":"PyTorch: An imperative style, highperformance deep learning library","volume-title":"in Proc. NeurIPS","author":"Paszke","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"in International conference on machine learning. PMLR","author":"Radford"},{"key":"ref18","year":"2025","journal-title":"Grok 3 beta - the age of reasoning agents"},{"key":"ref19","first-page":"2709","article-title":"Yourtts: Towards zero-shot multispeaker tts and zero-shot voice conversion for everyone","volume-title":"in International conference on machine learning. PMLR","author":"Casanova"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-299"}],"event":{"name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Yogyakarta, Indonesia","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11383559\/11384821\/11385248.pdf?arnumber=11385248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T06:54:23Z","timestamp":1771484063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11385248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda68185.2025.11385248","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}