{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:19Z","timestamp":1775229799102,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"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":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362120","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":23,"title":["Accent and Speaker Disentanglement in Many-to-many Voice Conversion"],"prefix":"10.1109","author":[{"given":"Zhichao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenshuo","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wendong","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiulin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref31","first-page":"5329","article-title":"X-VECTORS : ROBUST DNN EMBEDDINGS FOR SPEAKER RECOGNITION David Snyder , Daniel Garcia-Romero , Gregory Sell , Daniel Povey , Sanjeev Khudanpur Center for Language and Speech Processing & Human Language Technology Center of Excellence The Johns Hopkins Un","author":"snyder","year":"2018","journal-title":"ICASSP"},{"key":"ref30","article-title":"Visualizing data using t-SNE","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref14","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"2016 IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1514"},{"key":"ref17","article-title":"Zero-shot voice style transfer with only autoencoder loss","volume":"abs 1905 5879","author":"qian","year":"2019","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref27","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2177820"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038663"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref1","first-page":"556","article-title":"Vtln-based voice conversion","author":"sundermann","year":"2003","journal-title":"Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat No 03EX795)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003798"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2530"},{"key":"ref23","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682927"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025410"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Hong Kong","start":{"date-parts":[[2021,1,24]]},"end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362120.pdf?arnumber=9362120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:57Z","timestamp":1652197317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362120","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}