{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:25:55Z","timestamp":1764401155902,"version":"3.46.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249418","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1122-1127","source":"Crossref","is-referenced-by-count":0,"title":["Few-Shot Speaker Adaptation for Text-to-Speech Synthesis Using Non-Target Speaker Corpora for Glossectomy Patients"],"prefix":"10.1109","author":[{"given":"Masayori","family":"Okamura","sequence":"first","affiliation":[{"name":"Okayama University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masanobu","family":"Abe","sequence":"additional","affiliation":[{"name":"Okayama University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunao","family":"Hara","sequence":"additional","affiliation":[{"name":"Okayama University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"215","article-title":"Articulation dynamics after extensive glossectomy","volume":"26","author":"Ohira","year":"1985","journal-title":"The Japanese Journal of Voice and Speech Disorders"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1239"},{"key":"ref4","first-page":"1053","article-title":"Improving speech intelligibility for people with spinal muscular atrophy using speaker adaptation of acoustic models","author":"Yoshimoto","year":"2021","journal-title":"The 2021 Autumn Meeting of the Acoustic Society of Japan"},{"key":"ref5","first-page":"1045","article-title":"Improving speech intelligibility for people with spinal muscular atrophy using multi-speaker tts","author":"Yoshimoto","year":"2022","journal-title":"The 2022 Spring Meeting of the Acoustic Society of Japan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref7","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. ICML","author":"Casanova","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193459"},{"key":"ref9","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim","year":"2021"},{"key":"ref10","first-page":"13898","article-title":"Release of pretrained models for the Japanese language","volume-title":"Proc. LREC-COLING","author":"Sawada","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023168"},{"key":"ref15","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"Jia","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530270"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249418.pdf?arnumber=11249418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:20:54Z","timestamp":1764400854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249418","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}