{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:53:29Z","timestamp":1776182009767,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096285","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":58,"title":["Prompttts: Controllable Text-To-Speech With Text Descriptions"],"prefix":"10.1109","author":[{"given":"Zhifang","family":"Guo","sequence":"first","affiliation":[{"name":"Univerisity of Science and Technology of China, Renmin University of China,Microsoft Azure Speech, Microsoft Research Asia"}]},{"given":"Yichong","family":"Leng","sequence":"additional","affiliation":[{"name":"Univerisity of Science and Technology of China, Renmin University of China,Microsoft Azure Speech, Microsoft Research Asia"}]},{"given":"Yihan","family":"Wu","sequence":"additional","affiliation":[{"name":"Univerisity of Science and Technology of China, Renmin University of China,Microsoft Azure Speech, Microsoft Research Asia"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Univerisity of Science and Technology of China, Renmin University of China,Microsoft Azure Speech, Microsoft Research Asia"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Univerisity of Science and Technology of China, Renmin University of China,Microsoft Azure Speech, Microsoft Research Asia"}]}],"member":"263","reference":[{"key":"ref13","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 (ICML)"},{"key":"ref12","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1208"},{"key":"ref14","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Annual conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL)"},{"key":"ref20","article-title":"An objective measure for estimating mos of synthesized speech","author":"min","year":"2001","journal-title":"Conference of the International Speech Communication Association (InterSpeech)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-866"},{"key":"ref10","author":"bae","year":"2020","journal-title":"Speaking speed control of end-to-end speech synthesis using sentence-level conditioning"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/978-3-642-19551-8_23","article-title":"Speech quality assessment","author":"loizou","year":"2011","journal-title":"Multimedia Analysis Processing and Communications"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.12.003"},{"key":"ref1","author":"zeng","year":"2021","journal-title":"PanGu Large-scale Autore-gressive Pretrained Chinese Language Models with Auto-parallel Computation"},{"key":"ref17","article-title":"Simbert: Integrating retrieval and generation into bert","author":"su","year":"2020","journal-title":"Tech Rep"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref19","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Neural Information Processing Systems Conf (NIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref8","author":"tan","year":"2022","journal-title":"Naturalspeech End-to-end text to speech synthesis with human-level quality"},{"key":"ref7","author":"tan","year":"2021","journal-title":"A survey on neural speech synthesis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746323"},{"key":"ref4","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref6","author":"ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with CLIP latents"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Neural Information Processing Systems Conf (NIPS)"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096285.pdf?arnumber=10096285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:33Z","timestamp":1700507133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096285","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}