{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:31:03Z","timestamp":1777390263967,"version":"3.51.4"},"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"}],"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.2024.3407600","type":"journal-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T17:29:23Z","timestamp":1718040563000},"page":"2944-2956","source":"Crossref","is-referenced-by-count":14,"title":["Distinctive and Natural Speaker Anonymization via Singular Value Transformation-Assisted Matrix"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5324-7360","authenticated-orcid":false,"given":"Jixun","family":"Yao","sequence":"first","affiliation":[{"name":"Audio, Speech and Langauge Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5449-4815","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"Audio, Speech and Langauge Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2388-5935","authenticated-orcid":false,"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Audio, Speech and Langauge Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqian","family":"Ning","sequence":"additional","affiliation":[{"name":"Audio, Speech and Langauge Processing Group (ASLP@NPU), 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":"Audio, Speech and Langauge Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2983"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2002.1134447"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2647"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101362"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095120"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1333"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101362"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1070"},{"key":"ref12","first-page":"543","article-title":"Design of voice privacy system using linear prediction","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Gupta","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.010"},{"key":"ref14","article-title":"Adjustable deterministic pseudonymisation of speech: Idiap-nkis submission to voiceprivacy 2020 challenge","author":"Dubagunta","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/spsc.2022-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274855"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383529"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.05.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190741"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3313429"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-39"},{"key":"ref22","article-title":"NWPU-ASLP system for the voiceprivacy 2022 challenge","author":"Yao","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2692"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1887"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref31","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref32","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746278"},{"key":"ref34","article-title":"A praat plugin for momel and INTSINT with improved algorithms for modeling and coding intonation","volume-title":"Proc. ICPhS, 16th Int. Congr. Phonetic Sci.","author":"Hirst","year":"2007"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101299"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2720"},{"key":"ref38","volume-title":"Spectral Fusion, Spectral Parsing and the Formation of Auditory Images","author":"McAdams","year":"1984"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1038"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101351"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022601"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101318"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10703"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096607"},{"key":"ref46","article-title":"A study of f0 modification for x-vector based speech pseudonymization across gender","author":"Champion","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313429"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743729"},{"key":"ref51","article-title":"Mega-TTS 2: Zero-shot text-to-speech with arbitrary length speech prompts","author":"Jiang","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-381460-9.00002-X"},{"key":"ref53","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref55","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref59","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\/ielx8\/6570655\/10304349\/10552337.pdf?arnumber=10552337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T20:52:44Z","timestamp":1719348764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10552337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3407600","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}