The speech signal conveys information about the identity of the speaker. The area of speaker identification is concerned with extracting the identity of the person speaking the utterance. As understanding how to recognize complex, unstructured, and high-dimensional voice/speech/audio data is one of the greatest challenges of our time.
In this project, we proposed an idea for identity of a speaker by machine on the basis of his/her voice with the help of deep learning approach. This proposed work ensures the accuracy of 98.35% using MLP, 99.17% using CNN, 98.35% using RNN, 99.67% using LSTM and 97.52 using GRU.