{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:00Z","timestamp":1764400260128,"version":"3.46.0"},"reference-count":21,"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\/apsipaasc65261.2025.11249304","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"801-806","source":"Crossref","is-referenced-by-count":0,"title":["Improving Speech-to-Speech Translation for Low-Resource Languages via Transfer Learning"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhou","sequence":"first","affiliation":[{"name":"Graduate School of Engineering, Tohoku University,Sendai,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University,Sendai,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University,Sendai,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"issue":"7","key":"ref2","article-title":"Translatotron 2: Robust direct speech-to-speech translation","volume":"6","author":"Jia","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","first-page":"3327","article-title":"Direct speech-tospeech translation with discrete units","volume-title":"Proc. ACL","volume":"1","author":"Lee","year":"2022"},{"key":"ref5","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref7","article-title":"Transpeech: Speech-tospeech translation with bilateral perturbation","volume-title":"Proc. ICLR","author":"Huang","year":"2023"},{"key":"ref8","first-page":"15655","article-title":"Unity: Twopass direct speech-to-speech translation with discrete units","volume-title":"Proc. ACL","volume":"1","author":"Inaguma","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/sym11020179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300540"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3486711"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1227"},{"key":"ref13","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":"ref14","article-title":"End-to-end text-to-speech for low-resource languages by cross-lingual transfer learning","author":"Tu","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00225-4"},{"key":"ref16","first-page":"6691","article-title":"Cvss corpus and massively multilingual speech-tospeech translation","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Jia","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-023-09704-w"},{"issue":"97","key":"ref19","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-demo.6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"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\/11249304.pdf?arnumber=11249304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:06:12Z","timestamp":1764399972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249304","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}