{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:47:06Z","timestamp":1778604426709,"version":"3.51.4"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747319","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8322-8326","source":"Crossref","is-referenced-by-count":14,"title":["Cloning One\u2019s Voice Using Very Limited Data in the Wild"],"prefix":"10.1109","author":[{"given":"Dongyang","family":"Dai","sequence":"first","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Tu","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019"},{"key":"ref3","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref5","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018"},{"key":"ref12","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref8","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":"ref7","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747319.pdf?arnumber=9747319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:17Z","timestamp":1660594277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747319","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}