{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T00:23:04Z","timestamp":1723854184501},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10627128","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"341-345","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Self-Supervised Features for Expressive, Multilingual Voice Conversion"],"prefix":"10.1109","author":[{"given":"\u00c1lvaro","family":"Mart\u00edn-Cortinas","sequence":"first","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"S\u00e1ez-Trigueros","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grzegorz","family":"Beringer","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iv\u00e1n","family":"Vall\u00e9s-P\u00e9rez","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Barra-Chicote","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biel","family":"Tura-Vecino","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Gabry\u015b","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Merritt","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Bili\u0144ski","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Lorenzo-Trueba","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proceedings of ICML","author":"Qian","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746368"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IC_ASET53395.2022.9765886"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362110"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3193761"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10023428","article-title":"Exploration of a self-supervised speech model: A study on emotional corpora","volume-title":"SLT","author":"Li"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10023234","article-title":"On the utility of self-supervised models for prosody-related tasks","volume-title":"SLT","author":"Lin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"International Conference on Learning Representations","author":"Lee","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"International Conference on Language Resources and Evaluation","author":"Ardila","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2194"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1367"},{"key":"ref26","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2307\/4615733"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10627128.pdf?arnumber=10627128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:52:28Z","timestamp":1723787548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10627128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10627128","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}