{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:48:59Z","timestamp":1762508939132,"version":"3.28.0"},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037585","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"319-323","source":"Crossref","is-referenced-by-count":5,"title":["AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation"],"prefix":"10.1109","author":[{"given":"Kun","family":"Song","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Software,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cong","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongmao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Yang","sequence":"additional","affiliation":[{"name":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, ser. Proceedings of Machine Learning Research","volume":"139","author":"Kim"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Ren"},{"key":"ref4","first-page":"14 881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Kumar"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref6","first-page":"10 040","article-title":"Neural voice cloning with a few samples","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018","author":"Arik"},{"volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Chen","article-title":"Sample efficient adaptive text-to-speech","key":"ref7"},{"key":"ref8","article-title":"Adaspeech: Adaptive text to speech for custom voice","volume":"abs\/2103.00993","author":"Chen","year":"2021","journal-title":"CoRR"},{"key":"ref9","article-title":"Meta-voice: Fast few-shot style transfer for expressive voice cloning using meta learning","volume":"abs\/2111.07218","author":"Liu","year":"2021","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2020-2530"},{"volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Ren","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","key":"ref11"},{"key":"ref12","article-title":"Distilling the knowledge in a neural network","volume":"abs\/1503.02531","author":"Hinton","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2020-1745"},{"key":"ref15","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, ser. Proceedings of Machine Learning Research","volume":"119","author":"Katharopoulos"},{"key":"ref16","article-title":"Visinger: Variational inference with adversarial learning for end-to-end singing voice synthesis","volume":"abs\/2110.08813","author":"Zhang","year":"2021","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.48550\/arXiv.1609.03499"},{"volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Lee","article-title":"Nanoflow: Scalable normalizing flows with sublinear parameter complexity","key":"ref18"},{"key":"ref19","article-title":"Universal melgan: A robust neural vocoder for high-fidelity waveform generation in multiple domains","volume":"abs\/2011.09631","author":"Jang","year":"2020","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.21437\/Interspeech.2020-2537"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2019-2441"},{"year":"2017","author":"Veaux","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.21437\/Interspeech.2021-1983"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/SLT48900.2021.9383551"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.21437\/Interspeech.2021-414"}],"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\/10037585.pdf?arnumber=10037585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:24:39Z","timestamp":1707830679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037585","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}