{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:28:49Z","timestamp":1740101329359,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008343","name":"Beijing Language and Culture University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008343","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10038178","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"225-229","source":"Crossref","is-referenced-by-count":0,"title":["AdaptiveFormer: A Few-shot Speaker Adaptive Speech Synthesis Model based on FastSpeech2"],"prefix":"10.1109","author":[{"given":"Dengfeng","family":"Ke","sequence":"first","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Ruixin","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Qi","family":"Luo","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Liangjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Wenhan","family":"Yao","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Wentao","family":"Shu","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]},{"given":"Yanlu","family":"Xie","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref2","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"Ping","year":"2017","journal-title":"arXiv preprint arXiv:1710.07654"},{"key":"ref3","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746875"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2103.00993"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3167258"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746049"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref15","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref17","article-title":"Neural voice cloning with a few samples","volume":"31","author":"Arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref21","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10038178.pdf?arnumber=10038178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T14:07:24Z","timestamp":1707833244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10038178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10038178","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}