{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:32:05Z","timestamp":1773930725287,"version":"3.50.1"},"reference-count":71,"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 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":[[2023]]},"DOI":"10.1109\/taslp.2023.3313414","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T17:38:56Z","timestamp":1694194736000},"page":"3883-3895","source":"Crossref","is-referenced-by-count":5,"title":["MSM-VC: High-Fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-Scale Style Modeling"],"prefix":"10.1109","volume":"31","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\/0000-0003-1826-7419","authenticated-orcid":false,"given":"Xinsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qicong","family":"Xie","sequence":"additional","affiliation":[{"name":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5578-3960","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, 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":"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":"10.1109\/TASL.2007.907344"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2177820"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2333242"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746405"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-16"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2412"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687906"},{"key":"ref18","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":"ref19","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-19"},{"key":"ref23","first-page":"1","article-title":"Towards fine-grained prosody control for voice conversion","volume-title":"Proc. Int. Symp. Chin. Spoken Lang. Process.","author":"Lian","year":"2021"},{"key":"ref24","article-title":"IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion","author":"Gan","year":"2022"},{"key":"ref25","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S0952675700000695"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038056"},{"key":"ref30","first-page":"2021","article-title":"AdaSpeech: Adaptive text to speech for custom voice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10316"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref33","article-title":"VQ-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref36","article-title":"Emotional end-to-end neural speech synthesizer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref43","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hsu","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746994"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-13"},{"key":"ref46","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref48","first-page":"4683","article-title":"Fine-grained style modelling and transfer in text-to-speech synthesis via content-style disentanglement","volume-title":"Proc. Conf. Int. Speech Commun. Assoc.","author":"Tan","year":"2021"},{"key":"ref49","first-page":"4683","article-title":"Fine-grained style modeling, transfer and prediction in text-to-speech synthesis via phone-level content-style disentanglement","volume-title":"Proc. Conf. Int. Speech Commun. Assoc.","author":"Daxin","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3074757"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref52","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-838"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414137"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3203888"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2013.05.013"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658830"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref68","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref71","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10243636.pdf?arnumber=10243636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:30:12Z","timestamp":1709339412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313414","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}