CASIA OpenIR  > 模式识别国家重点实验室  > 语音交互
基于组块分析的韵律短语预测方法
陶建华; 董宏辉
2006-04-04
Date Available2007-10-10
CountryCN
Subtype发明
Abstract本发明涉及一种基于组块分析的韵律短语预测方法,用于语音合成系统韵律短语的预测,将系统接收或输入的任意文字串转换成带有韵律短语停顿标注的文字形式,将组块作为韵律短语预测的基本单元,训练生成组块合并模型;训练生成韵律短语边界必停点的预测模型;训练生成韵律短语的节律平衡模型;基于组块合并模型、韵律短语必停点的预测模型、长度约束模型执行生成韵律短语。创建韵律短语标注语料库,用组块从文本生成组块,利用韵律短语语料库估计组块合并模型、训练支持向量机识别器,得到韵律短语的必停点的预测器,利用韵律短语语料库训练节律平衡模型。本发明提高了韵律短语边界预测的准确率和召回率,使得合成结果保持较好的自然度和可懂度。
Copyright Date2011-02-09
Patent NumberCN200610073102.1
Status授权
Document Type专利
Identifierhttp://ir.ia.ac.cn/handle/173211/8206
Collection模式识别国家重点实验室_语音交互
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
陶建华,董宏辉. 基于组块分析的韵律短语预测方法. CN200610073102.1[P]. 2006-04-04.
Files in This Item:
File Name/Size DocType Version Access License
3-2011-基于组块分析的韵律短语预测(1178KB)专利 开放获取CC BY-NC-SAThumbnail
Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[陶建华]'s Articles
[董宏辉]'s Articles
Baidu academic
Similar articles in Baidu academic
[陶建华]'s Articles
[董宏辉]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[陶建华]'s Articles
[董宏辉]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.