{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:36:34Z","timestamp":1772642194470,"version":"3.50.1"},"reference-count":24,"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\/icassp48485.2024.10447871","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4725-4729","source":"Crossref","is-referenced-by-count":21,"title":["Speaker Anonymization Using Neural Audio Codec Language Models"],"prefix":"10.1109","author":[{"given":"Michele","family":"Panariello","sequence":"first","affiliation":[{"name":"Eurecom,France"}]},{"given":"Francesco","family":"Nespoli","sequence":"additional","affiliation":[{"name":"Microsoft,UK"}]},{"given":"Massimiliano","family":"Todisco","sequence":"additional","affiliation":[{"name":"Eurecom,France"}]},{"given":"Nicholas","family":"Evans","sequence":"additional","affiliation":[{"name":"Eurecom,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1333"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101362"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10586"},{"key":"ref6","article-title":"A Study of F0 Modification for X-Vector Based Speech Pseudonymization Across Gender","author":"Champion","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref9","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023"},{"key":"ref10","article-title":"NWPU-ASLP System for the VoicePrivacy 2022 Challenge","volume-title":"Proc. 2nd Symposium on Security and Privacy in Speech Communication","author":"Yao"},{"key":"ref11","article-title":"Cascade of phonetic speech recognition, speaker embeddings gan and multispeaker speech synthesis for the VoicePrivacy 2022 Challenge","volume-title":"Proc. 2nd Symposium on Security and Privacy in Speech Communication","author":"Meyer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3313429"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2023-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-448"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref16","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3308474"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1341"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"8","key":"ref21","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447871.pdf?arnumber=10447871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:19:31Z","timestamp":1722579571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447871","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}