{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:24:37Z","timestamp":1785857077329,"version":"3.56.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3308474","type":"journal-article","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T17:31:01Z","timestamp":1692898261000},"page":"1157-1161","source":"Crossref","is-referenced-by-count":24,"title":["LM-VC: Zero-Shot Voice Conversion via Speech Generation Based on Language Models"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8075-1784","authenticated-orcid":false,"given":"Zhichao","family":"Wang","sequence":"first","affiliation":[{"name":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref2","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"Proc. Int. Conf. Mach. Learn.,","author":"Qian","year":"2020"},{"key":"ref3","article-title":"MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features","author":"Gu","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref5","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Choi","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref7","article-title":"Retriever: Learning content-style representation as a token-level bipartite graph","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yin","year":"2021"},{"key":"ref8","article-title":"Speaking style conversion with discrete self-supervised units","author":"Maimon","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref10","article-title":"Multi-level temporal-channel speaker retrieval for robust zero-shot voice conversion","author":"Wang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414487"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref16","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref17","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","article-title":"On using monolingual corpora in neural machine translation","author":"Gulcehre","year":"2015"},{"key":"ref22","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref26","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Dong","year":"2019"},{"key":"ref27","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref28","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref29","article-title":"Language model fusion for streaming end to end speech recognition","author":"Cabrera","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref33","first-page":"223","article-title":"The CMU Arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth.","author":"Kominek","year":"2004"},{"key":"ref34","article-title":"The EMIME bilingual database","author":"Wester","year":"2010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2013.05.013"},{"key":"ref38","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref39","article-title":"Megabyte: Predicting million-byte sequences with multiscale transformers","author":"Yu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.755"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10036333\/10229308.pdf?arnumber=10229308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T21:59:01Z","timestamp":1709330341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10229308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3308474","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}