Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 11 (2022) > Article

DOI: 10.14704/nq.2022.20.11.NQ66107

New Feature Vector Based Gender Identification System Using GMM –

Dr.B.Chandrasekaram

Abstract

In this paper a new feature vector for Gender Identification system using Guassian mixture model(GMM) is explored. From the literature it is found that In first using MFCC new type of feature vectors are created using a GMM probability density function. The conventional GMM based gender identification system require large amount of training data to capture all the gender discrimination information present in the speech signal. Where as the new feature vectors based gender Identification system require less amount training data. The performance of new feature vector based gender identification system is compared with the conventional MFCC based Gender identification system. From the analysis it is found that the performance of new feature vector based Gender identification system is outperform than the MFCC GMM based Gender identification system.

Keywords

Gender identification system, GMM, MFCC.

Full Text

PDF

References

?>