{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:37:08Z","timestamp":1776886628892,"version":"3.51.2"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3407577","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:56:23Z","timestamp":1717091783000},"page":"2926-2937","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Level Temporal-Channel Speaker Retrieval for Zero-Shot Voice Conversion"],"prefix":"10.1109","volume":"32","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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2815-8494","authenticated-orcid":false,"given":"Liumeng","family":"Xue","sequence":"additional","affiliation":[{"name":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4078-1273","authenticated-orcid":false,"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance SAMI Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"ref7","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":"ref8","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414081"},{"key":"ref10","article-title":"Mediumvc: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features","author":"Gu","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746048"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414487"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref20","first-page":"800","article-title":"CA-VC: A novel zero-shot voice conversion method with channel attention","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Xiao","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref24","first-page":"2021","article-title":"Retriever: Learning content-style representation as a token-level bipartite graph","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2512"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11305"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746049"},{"key":"ref29","first-page":"1861-1862","article-title":"Speech and audio signal processing: Processing and perception of speech and music, second edition","volume":"132","author":"Gold","year":"2012","journal-title":"J. Acoustical Soc. Amer."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-892"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref33","article-title":"Human voice"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096471"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref39","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923651"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018287"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Skerry-Ryan","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-610"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313414"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref52","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref53","first-page":"223","article-title":"The CMU arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth.","author":"Kominek","year":"2004"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref58","article-title":"TFGAN: Time and frequency domain based generative adversarial network for high-fidelity speech synthesis","author":"Tian","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10542423.pdf?arnumber=10542423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T20:52:46Z","timestamp":1719348766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3407577","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}