{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:14:17Z","timestamp":1767183257936,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB0204403,2017YFB1401202,2018YFB1003500"],"award-info":[{"award-number":["2018YFB0204403,2017YFB1401202,2018YFB1003500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688088","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"938-945","source":"Crossref","is-referenced-by-count":18,"title":["TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training"],"prefix":"10.1109","author":[{"given":"Huaizhen","family":"Tang","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Xiao","sequence":"additional","affiliation":[{"name":"Aquinas International Academy,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2365"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref14","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref17","first-page":"6309","article-title":"Neural discrete representation learning","author":"van den oord","year":"0","journal-title":"2017 Neural Information Processing Systems (NIPS)"},{"key":"ref18","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational autoencoder","author":"hsu","year":"2016","journal-title":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)"},{"key":"ref19","first-page":"1876","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"0","journal-title":"Annual Conference on Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref8","first-page":"6793","article-title":"Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","volume":"32","author":"serr\u00e0","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1710"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(89)90041-1"},{"key":"ref9","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":"ref20","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"gibiansky","year":"0","journal-title":"Annual Conference on Neural Information Processing Systems"},{"key":"ref22","first-page":"3171","article-title":"Fastspeech: fast, robust and controllable text to speech","author":"ren","year":"0","journal-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems(NeurIPS)"},{"key":"ref21","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"International Conference on Learning Representations(ICLR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688088.pdf?arnumber=9688088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:27Z","timestamp":1652201907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688088","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}