{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:20Z","timestamp":1764399080008,"version":"3.46.0"},"reference-count":32,"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"}],"funder":[{"DOI":"10.13039\/501100000646","name":"JSPS","doi-asserted-by":"publisher","award":["JP23H00493,JP25H00566"],"award-info":[{"award-number":["JP23H00493,JP25H00566"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11248972","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"986-991","source":"Crossref","is-referenced-by-count":0,"title":["Improving Automatic Speech Recognition Model for Super-Elderly Voice Using Speech Synthesis Model"],"prefix":"10.1109","author":[{"given":"Ryota","family":"Uematsu","sequence":"first","affiliation":[{"name":"University of Yamanashi,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee Siang","family":"Leow","sequence":"additional","affiliation":[{"name":"University of Yamanashi,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norihide","family":"Kitaoka","sequence":"additional","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiromitsu","family":"Nishizaki","sequence":"additional","affiliation":[{"name":"University of Yamanashi,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2010-525783"},{"journal-title":"Litagin02","article-title":"Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles","year":"2024","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414207"},{"key":"ref4","first-page":"294","article-title":"ASR TAMIL SSN@ LT-EDI-2024: Automatic Speech Recognition System for Elderly People","volume-title":"Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion, Association for Computational Linguistics","author":"Suhasini"},{"volume-title":"Elderly Adults Read Speech Corpus (EARS), Speech Resources Consortium, National Institute of Informatics. (dataset)","year":"2023","author":"Kitaoka","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101424"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref9","article-title":"Improving automated speech recognition using retrieval-based voice conversion","author":"Alhumud","year":"2024","journal-title":"The second tiny papers track at ICLR 2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LifeTech53646.2022.9754798"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2977776"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746582"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037859"},{"key":"ref15","article-title":"Deep Voice 3: 2000-Speaker Neural Text-to-Speech","volume-title":"International Conference on Learning Representations","author":"Ping","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref17","article-title":"FastSpeech: Fast, Robust and Controllable Text to Speech","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ren","year":"2019"},{"key":"ref18","first-page":"74 213","article-title":"P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Kim","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref21","article-title":"Deep speaker: an end-toend neural speaker embedding system","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3323888"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3422839"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1645"},{"key":"ref26","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"139","author":"Kim","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-534"},{"volume-title":"Fish Audio, Bert-vits2","year":"2024","key":"ref28"},{"key":"ref29","first-page":"28492","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202","author":"Radford","year":"2023"},{"volume-title":"Mainichi shimbun CD-ROM edition, CD-ROM database","year":"1995","author":"Shimbun","key":"ref30"},{"article-title":"ASJ Japanese Newspaper Article Sentences Read Speech Corpus (JNAS), Speech Resources Consortium, National Institute of Informatics","volume-title":"The Acoustical Society of Japan","year":"2006","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1250\/ast.20.199"}],"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\/11248972.pdf?arnumber=11248972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:49:48Z","timestamp":1764398988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11248972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11248972","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}