Continuous speech of speaker-independent based on two weight neural networks

被引：0

作者：

Cao Wen-ming ^{[1
]}

Ye Hong ^{[1
]}

Xu Chun-yan ^{[1
]}

Wang Shou-jue ^{[1
]}

机构：

[1] Zhejiang Univ Technol, Inst Intelligent Informat Syst, Informat Coll, Hangzhou 310014, Peoples R China

来源：

PROCEEDINGS OF 2005 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1 AND 2 | 2005年

关键词：

two weight neural networks; HMM; continuous digital speech;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Two weight neural network is described in this paper. a new dynamic searching algorithm based on two weight neural network is presented. And then it is applied to recognize the continuous speech of speaker-independent. The recognition results can be searched dynamically without endpoint detecting and segmenting. Different feature-space covers are constructed according to different classes of syllables. Compared with the conventional HMM-based method. The trend of recognition results shows that the difference of recognition rates between these two methods, decreases as the number of training increases, but the recognition rate oftwo weight neural network is always higher than that of HMM-based. And both of these recognition rates will reach 100% if there are enough training samples.

引用

页码：1415 / +

页数：4