期刊名称:International Journal of Engineering and Computer Science
印刷版ISSN:2319-7242
出版年度:2014
卷号:3
期号:8
页码:7874-7878
出版社:IJECS
摘要:In this paper, robust feature for Automatic text-independent Gender Identification System has been explored.Through different experimental studies, it is demonstrated that the timing varying speech related information can beeffectively captured using Hidden Markov Models (HMMs). The study on the effect of feature vector size for goodGender Identification demonstrates that, feature vector size in the range of 18-22 can capture Gender relatedinformation effectively for a speech signal sampled at 16 kHz, it is established that the proposed GenderIdentification system requires significantly less amount of data during both during training as well as in testing. TheGender Identification study using robust features for different states and different mixtures components, trainingand test duration has been exploited. I demonstrate the Gender Identification studies on TIMIT database
关键词:Gaussian Mixture Model (GMM); Gender; LPC; MFCC