Title :
Neural networks for improved text-independent speaker identification
Author :
Yue, Xicai ; Ye, Datian ; Zheng, Chongxun ; Wu, Xiaoyu
Author_Institution :
Dept. of Electr. Eng., Tsinghua Univ., Beijing, China
Abstract :
In this article, we consider the binary partitioned approach with pattern index information, propose an neural network array (NNA) that performs the pattern recognition task by combining the binary partitioned approach with decision trees, and verify that the NNA can not only reduce the computation cost of training and recognition but also reduce the classification error rate. Speaker identification with the radial basis function neural network array (RBFNNA) is discussed in detail as an application of the NNA.
Keywords :
decision trees; radial basis function networks; speaker recognition; binary partitioned approach; classification error rate reduction; complex classification problems handling; computation cost reduction; decision trees; radial basis function neural network array; Biomedical engineering; Neural networks; Pattern recognition; Algorithms; Databases, Factual; Humans; Male; Models, Biological; Neural Networks (Computer); Pattern Recognition, Automated; Phonetics; Reproducibility of Results; Sensitivity and Specificity; Speech; Speech Acoustics; Speech Perception; Voice Quality;
Journal_Title :
Engineering in Medicine and Biology Magazine, IEEE
DOI :
10.1109/MEMB.2002.1000186
