A Survey Paper on Gender Identification System using Speech Signal

Abstract

Gender is a critical statistic characteristic of individuals. This paper provides a survey of automatic human gender identification using speech signal characteristics and classifiers. A review of approaches exploiting information from human speech presented. Here, highlights of selection of speech features, their processing and different classifiers used for this purpose are discussed. Based on the results discussed in the papers it can be stated as, accuracy of automatic gender identification system with any classifiers is better if speech dataset used for training and testing is taken/ recorded in the same environments. Pitch is the basic feature of speech which distinguishes between adult man and woman. Other features like MFCC, LPC, RASTA-PLP also used for automatic gender identification. Neural Network, Support Vector Machine (SVM), Random Forest etc. are used for automatic gender identification through speech signal. Till now, many challenges are still available here to identify gender with acceptable accuracy in real life environmental speech where noise is acoustically added with human speech.