{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:48Z","timestamp":1740101748570,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094786","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["A Synthetic Corpus Generation Method for Neural Vocoder Training"],"prefix":"10.1109","author":[{"given":"Zilin","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[{"name":"Transsion, Shanghai"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Sipan","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Jinfeng","family":"Bai","sequence":"additional","affiliation":[{"name":"TAL Education Group,Beijing"}]},{"given":"Gang","family":"He","sequence":"additional","affiliation":[{"name":"TAL Education Group,Beijing"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-349"},{"article-title":"Universal melgan: A robust neural vocoder for high-fidelity waveform generation in multiple domains","year":"2020","author":"jang","key":"ref14"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"article-title":"Bigvgan: A universal neural vocoder with large-scale training","year":"2022","author":"lee","key":"ref11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","year":"2020","author":"chen","key":"ref2"},{"key":"ref1","article-title":"Portaspeech: Portable and high-quality generative text-to-speech","volume":"34","author":"ren","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-806"},{"article-title":"Neural pitch-shifting and time-stretching with controllable lpcnet","year":"2021","author":"morrison","key":"ref16"},{"article-title":"Simulating content consistent vehicle datasets with attribute descent","year":"2019","author":"yao","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10222"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/072294b0"},{"article-title":"The chamber ensemble generator: Limitless high-quality mir data via generative modeling","year":"2022","author":"wu","key":"ref23"},{"key":"ref26","article-title":"Ddsp: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.1993.379970"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref22","article-title":"Self-supervised pitch detection by inverse audio synthesis","author":"engel","year":"2020","journal-title":"ICML 2020 Workshop on Self-supervision in Audio and Speech"},{"key":"ref21","first-page":"3","article-title":"One billion audio sounds from gpu-enabled modular synthesis","volume":"20","author":"turian","year":"2021","journal-title":"Synthesis"},{"article-title":"Voice cloning toolkit for festival and hts","year":"2010","author":"yamagishi","key":"ref28"},{"journal-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref8","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172092"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094786.pdf?arnumber=10094786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:59:02Z","timestamp":1700506742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094786\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094786","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}