{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T01:12:20Z","timestamp":1770340340250,"version":"3.49.0"},"reference-count":27,"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"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746765","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6082-6086","source":"Crossref","is-referenced-by-count":3,"title":["Context-Aware Mask Prediction Network for End-to-End Text-Based Speech Editing"],"prefix":"10.1109","author":[{"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqun","family":"Deng","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688051"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref12","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref13","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018"},{"key":"ref14","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref16","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"2016 IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073702"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"202","DOI":"10.21437\/SSW.2016-33","article-title":"Merlin: An open source neural network speech synthesis system","author":"wu","year":"2016","journal-title":"SSW"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414633"},{"key":"ref27","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref3","author":"jin","year":"2018","journal-title":"Speech synthesis for text-based editing of audio narration"},{"key":"ref6","article-title":"An experimental comparison of multiple vocoder types","author":"hu","year":"2013","journal-title":"Eighth ISCA Workshop on Speech Synthesis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref7","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985759"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9780080470948"},{"key":"ref20","author":"veaux","year":"2017","journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref25","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09746765.pdf?arnumber=9746765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:28Z","timestamp":1661199088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746765","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}