{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T02:30:08Z","timestamp":1768012208830,"version":"3.49.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095973","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Speech-To-Speech Translation with Multiple TTS Targets"],"prefix":"10.1109","author":[{"given":"Jiatong","family":"Shi","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Tang","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Lee","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirofumi","family":"Inaguma","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Pino","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-150"},{"key":"ref35","article-title":"ESPnet2-TTS: Extending the edge of TTS research","author":"hayashi","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref15","first-page":"928","article-title":"Libris2s: A german-english speech-to-speech translation corpus","author":"jeuris","year":"2022","journal-title":"LREC"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref14","first-page":"6691","article-title":"CVSS corpus and massively multilingual speech-to-speech translation","author":"jia","year":"2022","journal-title":"LREC"},{"key":"ref36","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2018","journal-title":"ICLRE"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref30","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref10","article-title":"Direct simultaneous speech to speech translation","author":"ma","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref32","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MDM.2013.99"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599563"},{"key":"ref17","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ICLRE"},{"key":"ref16","article-title":"Non-attentive Tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling","author":"shen","year":"2020","journal-title":"arXiv preprint arXiv 2010 09084"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref18","article-title":"Fisher and CALLHOME spanish–english speech translation","author":"post","year":"2014","journal-title":"Web Download Philadelphia Linguistic Data Consortium"},{"key":"ref24","article-title":"On generative spoken language modeling from raw audio","author":"lakhotia","year":"2021","journal-title":"TACL"},{"key":"ref23","article-title":"Discretalk: Text-to-speech as a machine translation problem","author":"hayashi","year":"2020","journal-title":"arXiv preprint arXiv 2005 05525"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660081"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref28","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383496"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17684"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref3","article-title":"Preserving word-level emphasis in speech-to-speech translation","author":"do","year":"2016","journal-title":"TASLP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10938"},{"key":"ref5","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","author":"jia","year":"2022","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095973.pdf?arnumber=10095973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:26Z","timestamp":1700507366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095973","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}