{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:43:01Z","timestamp":1730230981412,"version":"3.28.0"},"reference-count":23,"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\/icassp43922.2022.9746425","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6087-6091","source":"Crossref","is-referenced-by-count":1,"title":["A Study on the Efficacy of Model Pre-Training In Developing Neural Text-to-Speech System"],"prefix":"10.1109","author":[{"given":"Guangyan","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering"}]},{"given":"Yichong","family":"Leng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Daxin","family":"Tan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering"}]},{"given":"Ying","family":"Qin","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China,100044"}]},{"given":"Kaitao","family":"Song","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech"}]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"article-title":"Cuhk-ee voice cloning system for icassp 2021 m2voc challenge","year":"2021","author":"tan","key":"ref11"},{"journal-title":"Text-to-Speech Synthesis","year":"2009","author":"paul alexander","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1075\/lllt.17.24aoy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2016394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820818"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743752"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"1293","article-title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","author":"he","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref5","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref8","first-page":"10040","article-title":"Neural voice cloning with a few samples","author":"ar?k","year":"2018","journal-title":"Proc NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"article-title":"A survey on neural speech synthesis","year":"2021","author":"tan","key":"ref1"},{"key":"ref9","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2018","journal-title":"Proc ICLR"},{"key":"ref20","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Proc NIPS"},{"key":"ref22","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"}],"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\/09746425.pdf?arnumber=9746425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:10:28Z","timestamp":1660579828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746425","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}