{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T00:03:13Z","timestamp":1746230593507,"version":"3.28.0"},"reference-count":19,"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\/icassp43922.2022.9747155","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7232-7236","source":"Crossref","is-referenced-by-count":2,"title":["HiFiDenoise: High-Fidelity Denoising Text to Speech with Adversarial Networks"],"prefix":"10.1109","author":[{"given":"Lichao","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqun","family":"Deng","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"ren","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref15","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"article-title":"High fidelity speech synthesis with adversarial networks","year":"2019","author":"bi?kowski","key":"ref16"},{"article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","year":"2020","author":"chen","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"146","DOI":"10.21437\/SSW.2016-24","article-title":"Investigating rnn-based speech enhancement methods for noise-robust text-to-speech","author":"valentini-botinhao","year":"2016","journal-title":"SSW"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"article-title":"Noise robust tts for low resource speakers using pretrained model and speech enhancement","year":"2020","author":"dai","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"article-title":"Hierarchical generative modeling for controllable speech synthesis","year":"2018","author":"hsu","key":"ref7"},{"article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","year":"2016","author":"veaux","key":"ref2"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413934"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747155.pdf?arnumber=9747155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:47Z","timestamp":1660594247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747155","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}