{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:30:11Z","timestamp":1730230211813,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413934","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"7063-7067","source":"Crossref","is-referenced-by-count":20,"title":["Denoispeech: Denoising Text to Speech with Frame-Level Noise Modeling"],"prefix":"10.1109","author":[{"given":"Chen","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Jinglin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kejun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc Interspeech 2017"},{"article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","year":"2016","author":"veaux","key":"ref11"},{"key":"ref12","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":"ref13","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"},{"article-title":"Uwspeech: Speech to speech translation for unwritten languages","year":"2020","author":"zhang","key":"ref14"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015 Conference Track Proceedings"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"article-title":"Noise robust tts for low resource speakers using pre-trained model and speech enhancement","year":"2020","author":"dai","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref6","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text-to-speech","year":"2020","author":"ren","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref9","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"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413934.pdf?arnumber=9413934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:41:07Z","timestamp":1652182867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413934","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}