Machine Learning based Gender Voice Recognition

Abstract

Gender Recognition (GR) means recognizing the gender of the person whether the person is men or
women. It is a significant task for human beings, as many communal functions precariously rely upon
correct gender awareness. Automatic human GR by machines has currently received symbolic
attention in computer vision community. Features like face, 3D body shape, gait (manner of walking),
footwear, fundamental frequency of voice etc are used for gender recognition. The ability to do
automatic recognition of human gender is essential for several systems that process or exploit humansource information. Common examples are information retrieval, human computer, or human-robot
intercommunication. The result of an AGR system can be used for achieving meta-data information
useful for annotating audio files. Moreover, gender is an important cue that can be exploited for
improving intelligibility of man-machine interaction, or just, for decreasing the investigation space in
applications such as speaker recognition or surveillance systems. Gender recognition has great
importance in forensics, games, business intelligence, demographic survey, visual surveillance. It is
completely known that human’s speech encloses linguistic content, identity as well as the emotion of
speaker.