Zobrazeno 1 - 10
of 358
pro vyhledávání: '"Zhang, ShaoFei"'
The expressive quality of synthesized speech for audiobooks is limited by generalized model architecture and unbalanced style distribution in the training data. To address these issues, in this paper, we propose a self-supervised style enhancing meth
Externí odkaz:
http://arxiv.org/abs/2312.12181
Autor:
Walsh, Brendan, Hamilton, Mark, Newby, Greg, Wang, Xi, Ruan, Serena, Zhao, Sheng, He, Lei, Zhang, Shaofei, Dettinger, Eric, Freeman, William T., Weimer, Markus
An audiobook can dramatically improve a work of literature's accessibility and improve reader engagement. However, audiobooks can take hundreds of hours of human effort to create, edit, and publish. In this work, we present a system that can automati
Externí odkaz:
http://arxiv.org/abs/2309.03926
In this paper, we present MuLanTTS, the Microsoft end-to-end neural text-to-speech (TTS) system designed for the Blizzard Challenge 2023. About 50 hours of audiobook corpus for French TTS as hub task and another 2 hours of speaker adaptation as spoke
Externí odkaz:
http://arxiv.org/abs/2309.02743
Autor:
Xiao, Yujia, Zhang, Shaofei, Wang, Xi, Tan, Xu, He, Lei, Zhao, Sheng, Soong, Frank K., Lee, Tan
While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i) ignorance of cr
Externí odkaz:
http://arxiv.org/abs/2307.00782
Recent advancements in neural end-to-end TTS models have shown high-quality, natural synthesized speech in a conventional sentence-based TTS. However, it is still challenging to reproduce similar high quality when a whole paragraph is considered in T
Externí odkaz:
http://arxiv.org/abs/2209.06484
Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is costly to
Externí odkaz:
http://arxiv.org/abs/2206.12559
Autor:
Deng, Yue, Wang, Tingting, Sun, Qingpeng, Guo, Junxia, Sun, Jinfeng, Liu, Gang, Wang, Liwei, Wang, Dianlong, Zhang, Shaofei
Publikováno v:
In Journal of Alloys and Compounds 5 November 2024 1004
Autor:
Deng, Yue, Tan, Linli, Wang, Tingting, Bai, Shi, Sun, Jinfeng, Guo, Junxia, Li, Tiantian, Liu, Gang, Zhang, Shaofei
Publikováno v:
In International Journal of Hydrogen Energy 28 October 2024 88:199-208
Autor:
Zhang, Han-Ming, Zuo, Lihao, Li, Jiakang, Zhang, Shaofei, Guo, Junxia, Li, Xiao-Pu, Liu, Gang, Wang, Peng, Sun, Jinfeng
Publikováno v:
In Journal of Materials Science & Technology 10 July 2024 187:123-140
Autor:
Zhou, Ruochen, Ye, Mengting, OuYang, Xu, Zhang, ShaoFei, Zheng, SiYuan, Wang, Ruoqi, Cao, Panpan, Yang, Kefei, Zhou, Xiaoqin
Publikováno v:
In Schizophrenia Research May 2024 267:122-129