{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:28:11Z","timestamp":1738128491386,"version":"3.33.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848991","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Improving Speaker Consistency in Speech-to-Speech Translation Using Speaker Retention Unit-to-Mel Techniques"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhou","sequence":"first","affiliation":[{"name":"Tohoku University,Graduate School of Engineering,Sendai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[{"name":"Tohoku University,Graduate School of Engineering,Sendai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[{"name":"Tohoku University,Graduate School of Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","year":"2016","author":"B\u00e9rard","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"article-title":"Translatotron 2: Robust direct speech-to-speech translation","year":"2021","author":"Jia","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-648"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-srw.5"},{"key":"ref10","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Advances in neural information processing systems","volume":"32","author":"Ren"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17684"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.307"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"ref14","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Advances in neural information processing systems","volume":"31","author":"Jia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"Ren","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.08.015"},{"article-title":"Cvss corpus and massively multilingual speech-to-speech translation","year":"2022","author":"Jia","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101622"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Pratap","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-demo.6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"journal-title":"SpeechBrain: A general-purpose speech toolkit","year":"2021","author":"Ravanelli","key":"ref30"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848991.pdf?arnumber=10848991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:45Z","timestamp":1738045425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848991","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}