The NLPR Speech Synthesis entry for Blizzard Challenge 2020

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	The NLPR Speech Synthesis entry for Blizzard Challenge 2020
	Wang T(汪涛)
	2020-04
会议名称	INTERSPEECH 2020
会议日期	2020
会议地点	Online
摘要	The paper describes the NLPR speech synthesis system entry for Blizzard Challenge 2020. More than 9 hours of speech data from an news anchor and 3 hours of speech from one native Shanghainese speaker are adopted as training data for building system this year. Our speech synthesis system is built based on the multi-speaker end-to-end speech synthesis system. LPCNet based neural vocoder is adapted to improve the quality. Different from our previous system, some improvements about data pruning and speaker adaptation strategies were made to improve the stability of our system. In this paper, the whole system structure, data pruning method, and the duration control will be introduced and discussed. In addition, this competition includes two tasks of Mandarin and Shanghainese, and we will introduce the important parts of each topic respectively. Finally, the results of listening test are presented.
七大方向——子方向分类	智能交互
国重实验室规划方向分类	语音语言处理
是否有论文关联数据集需要存交	否
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/52363
专题	多模态人工智能系统全国重点实验室_模式分析与学习
作者单位	Institute of Automation, Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Wang T. The NLPR Speech Synthesis entry for Blizzard Challenge 2020[C],2020.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
BC20_NLPR.pdf（305KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载