CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
一种声调评测方法
柯登峰; 徐波; 王士进; 陈振标; 李宏言
2011-11-18
Date Available2012-04-18
CountryCN
Subtype发明
Abstract本发明公开了一种声调评测方法。该方法包括:从待评测语音中提取声调识别特征,声调识别特征包含基频曲线特征;将声调识别特征送入训练后的声调识别模型,获得每一个声调的识别得分;提取得分最高的声调及其识别得分作为第一评测特征,标准声调和标准声调识别得分作为第二评测特征;将第一声调评测特征和第二声调评测特征合并成4维的声调评测特征,送入训练后的声调评测模型,获得待评测语音的声调评测得分。本发明声调评测方法可以获得更加良好的声调评测性能。
Patent NumberCN201110370038.4
Status授权
Document Type专利
Identifierhttp://ir.ia.ac.cn/handle/173211/8592
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
柯登峰,徐波,王士进,等. 一种声调评测方法. CN201110370038.4[P]. 2011-11-18.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[柯登峰]'s Articles
[徐波]'s Articles
[王士进]'s Articles
Baidu academic
Similar articles in Baidu academic
[柯登峰]'s Articles
[徐波]'s Articles
[王士进]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[柯登峰]'s Articles
[徐波]'s Articles
[王士进]'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.