{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:00:15Z","timestamp":1776445215344,"version":"3.51.2"},"reference-count":20,"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\/iscslp57327.2022.10038120","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"71-75","source":"Crossref","is-referenced-by-count":5,"title":["Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS"],"prefix":"10.1109","author":[{"given":"Kun","family":"Song","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cong","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongmao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiying","family":"Wu","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref4","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Kalchbrenner"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref7","first-page":"7706","article-title":"Waveflow: A compact flow-based model for raw audio","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020","volume":"119","author":"Ping"},{"key":"ref8","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"9th International Conference on Learning Representations, ICLR 2021","volume":"2021","author":"Kong"},{"key":"ref9","first-page":"14881","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","volume":"2019","author":"Kumar"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref11","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","volume":"2020","author":"Kong"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"issue":"1","key":"ref15","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref18","first-page":"2756","article-title":"AISHELL-3: A multispeaker mandarin TTS corpus","volume-title":"Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association","volume":"2021","author":"Shi"},{"key":"ref19","article-title":"Delightfultts: The microsoft speech synthesis system for blizzard challenge 2021","volume":"abs\/2110.12612","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,12,11]]},"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\/10038120.pdf?arnumber=10038120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:31:25Z","timestamp":1709404285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10038120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10038120","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}