{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:25Z","timestamp":1737176845352,"version":"3.33.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832297","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"742-749","source":"Crossref","is-referenced-by-count":0,"title":["Discrete Unit Based Masking For Improving Disentanglement in Voice Conversion"],"prefix":"10.1109","author":[{"given":"Philip H.","family":"Lee","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA"}]},{"given":"Ismail Rasim","family":"Ulgen","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA"}]},{"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936599"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036784"},{"key":"ref7","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096642"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446160"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003979"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3267833"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414851"},{"key":"ref18","article-title":"Mel-spectrogram augmentation for sequence to sequence voice conversion","volume":"abs\/2001.01401","author":"Hwang","year":"2020","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11278"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096057"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"article-title":"Club: A contrastive log-ratio upper bound of mutual information","volume-title":"International Conference on Machine Learning","author":"Cheng","key":"ref28"},{"article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref35","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Casanova"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832297.pdf?arnumber=10832297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:10:58Z","timestamp":1737101458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832297","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}