Who is Speaking? Male or Female

Master's Thesis from the year 2013 in the subject Computer Science - Miscellaneous grade: A+ University of Manchester language: English abstract: The aim of this project was to create a gender identification system that can beused to identify the gender of the speaker. In this dissertation I have explained thesignal processing background such as Fourier transforms and DCT etc. that wasneeded to understand the underlying signal processing happening in digital devices.Apart from that I also investigated the different classification techniques such asAdaboost and Gaussian Mixture Models and different types of methods such asFusion method acoustic methods and pitch methods used in gender identification.From this perspective I have implemented 3 types of models (4 Models) thatare explained in the literature and introducing a new method for gender recognitionthat uses SDC feature with pitch to identify the gender. All models were testedand trained on the same amount of speech. The SDC and SDC fused model gavesatisfactory results on Voxforge dataset. Finally I tested the acoustic and fusedmodels on YouTube video which gave almost 90% accuracy. The results of myimplementations are shown in chapter 6.