Automatic Speaker Recognition using Mel Frequency Cepstral Coefficients (MFCC) and Fast Fourier Transform (FFT)

Loading...
Thumbnail Image

Date

2025

Journal Title

Journal ISSN

Volume Title

Publisher

University of Msila

Abstract

This work focuses on automatic speaker verification identity via his voice, which is a recent task of the Automatic Speaker Recognition field. This work is divided into two phases: The first phase "called training or learning phase" consists of acquiring and saving audio recordings of a group of speakers into PC. In the second phase "testing phase", an anonymous speech is introduced and compared its characteristics with the characteristics of previous recordings, using a set of algorithms (such as: MFCC, FFT) to make a decision. The speech files that were recorded and processed in this work are obtained using a personal computer microphone instead of special equipment, which explains the weakness of the obtained results.

Description

Keywords

Citation

Collections