{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:06:47Z","timestamp":1776881207156,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389719","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["Salt: Distinguishable Speaker Anonymization Through Latent Space Transformation"],"prefix":"10.1109","author":[{"given":"Yuanjun","family":"Lv","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixun","family":"Yao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peikun","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Lu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2816338"},{"key":"ref2","journal-title":"Regulation (EU) 2016\/679 of the European Parliament and of the Council"},{"key":"ref3","article-title":"The voiceprivacy 2022 challenge evaluation plan","volume":"abs\/2203.12468","author":"Tomashenko","year":"2022","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2022-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10703"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref7","first-page":"543","article-title":"Design of voice privacy system using linear prediction","volume-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Gupta"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1887"},{"key":"ref9","article-title":"A study of F0 modification for x-vector based speech pseudonymization across gender","volume":"abs\/2101.08478","author":"Champion","year":"2021","journal-title":"CoRR"},{"key":"ref10","article-title":"Speaker anonymization with distribution-preserving xvector generation for the voiceprivacy challenge 2020","volume":"abs\/2010.13457","author":"Turner","year":"2020","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","first-page":"15637","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Hendrycks"},{"key":"ref14","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Kong"},{"key":"ref15","article-title":"NWPU-ASLP system for the voiceprivacy 2022 challenge","volume":"abs\/2209.11969","author":"Yao","year":"2022","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3206084"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","volume-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2720"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101299"},{"key":"ref21","volume-title":"A praat plugin for momel and intsint with improved algorithms for modelling and coding intonation","author":"Hirst","year":"2007"},{"key":"ref22","article-title":"Robust speech recognition via large-scale weak supervision","volume":"abs\/2212.04356","author":"Radford","year":"2022","journal-title":"CoRR"},{"key":"ref23","article-title":"U2++: unified two-pass bidirectional end-to-end model for speech recognition","volume":"abs\/2106.05642","author":"Wu","year":"2021","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1417"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref28","article-title":"Speechbrain: A general-purpose speech toolkit","volume":"abs\/2106.04624","author":"Ravanelli","year":"2021","journal-title":"CoRR"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389719.pdf?arnumber=10389719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:42:36Z","timestamp":1706010156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389719","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}