{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:12:21Z","timestamp":1725808341389},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447144","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10181-10185","source":"Crossref","is-referenced-by-count":2,"title":["A Unified Front-End Framework for English Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Zelin","family":"Ying","sequence":"first","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Dong","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Huo","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324914000175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054695"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1472"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053390"},{"article-title":"Unified mandarin tts front-end based on distilled bert model","year":"2020","author":"Zhang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3273414"},{"key":"ref10","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT","author":"Ming-Wei Chang Kenton"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.163"},{"article-title":"RNN approaches to text normalization: A challenge","year":"2016","author":"Sproat","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.418"},{"article-title":"Transformer-based models of text normalization for speech applications","year":"2022","author":"Ro","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00349"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746051"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846248"},{"article-title":"Fixing weight decay regularization in adam, iclr 2018 conference","volume-title":"International Conference on Learning Representations (ICLR)","author":"Loshchilov","key":"ref21"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447144.pdf?arnumber=10447144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:30:29Z","timestamp":1722576629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447144","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}