Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Zengqiang Shang"'
Publikováno v:
Applied Sciences, Vol 13, Iss 2, p 868 (2023)
End-to-end text-to-speech (TTS) models that directly generate waveforms from text are gaining popularity. However, existing end-to-end models are still not natural enough in their prosodic expressiveness. Additionally, previous studies on improving t
Externí odkaz:
https://doaj.org/article/42a57d05ab6243e9a9b6471c1caa5642
Publikováno v:
2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP).
Publikováno v:
Applied Acoustics. 203:109183
Publikováno v:
Interspeech 2021.
Publikováno v:
Interspeech 2021.
Publikováno v:
ICASSP
In this paper, we introduce the low resource text-to-speech system from the ThinkIT team submitted to Multi-Speaker Multi-Style Voice Cloning Challenge (M2VoC). The challenge has two tasks: few-shot track1 provides 100 samples for each person and one
Autor:
He Li1 chungbuk@163.com, Xiaoxiao Niu1 15637863325@163.com, Li Ding1 604295294@qq.com, Tahir, Ali Shahid1 3508313416@qq.com, Changle Guo1 1943235984@qq.com, Jiajun Chai1 118728973@qq.com, Kaifei Zhang1 zhangkaifei1220@163.com, Shangshang Cheng1 1228274702@qq.com, Yiqiu Zhao1 670501084@qq.com, Yahui Zhang1 2013454114@qq.com, Yigao Xu1 1003288622@qq.com, Zengqiang Shang1 17337309582@163.com
Publikováno v:
International Journal of Agricultural & Biological Engineering. May2021, Vol. 14 Issue 3, p32-45. 14p.