{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:55:12Z","timestamp":1777503312644,"version":"3.51.4"},"reference-count":28,"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\/icassp48485.2024.10447984","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10326-10330","source":"Crossref","is-referenced-by-count":16,"title":["Wav2vec-VC: Voice Conversion via Hidden Representations of Wav2vec 2.0"],"prefix":"10.1109","author":[{"given":"Jaemin","family":"Lim","sequence":"first","affiliation":[{"name":"PrairieSchooner Inc,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"PrairieSchooner Inc,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref2","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Exploring wav2vec 2.0 on speaker verification and language identification","author":"Fan","year":"2020"},{"key":"ref6","article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","author":"Shah","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref10","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747434"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref22","article-title":"Facebook AI research sequence-to-sequence toolkit"},{"key":"ref23","article-title":"Cross-lingual multi-speaker text-to-speech synthesis for voice cloning without using parallel corpus for unseen speakers","author":"Liu","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref25","article-title":"Towards achieving robust universal neural vocoding","author":"Lorenzo-Trueba","year":"2018"},{"key":"ref26","article-title":"The cmu arctic speech databases","volume-title":"Fifth ISCA workshop on speech synthesis","author":"Kominek"},{"key":"ref27","volume-title":"Resemblyzer: a python package to analyze and compare voices with deep learning"},{"key":"ref28","volume-title":"Silero models: pre-trained enterprise-grade STT \/ TTS models and benchmarks"}],"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\/10447984.pdf?arnumber=10447984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:33:10Z","timestamp":1722580390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447984","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}