Voice-Based Human Identification using Machine Learning

Voice and natural language processing, is at the forefront of any human-machine interaction domain. Speech is an effortless and usable method of communication that is based on the sound waves generated by the speaker. It permits the machine to identify and comprehend human spoken language through speech signal processing and pattern recognition. In this work, a methodology for speaker recognition based on machine learning algorithms is proposed. Support Vector Machine (SVM) and Random Forest (RF) models are used with statistical features and Mel-Frequency Cepstral Coefficients (MFCC) as the input features of the models. A new voice dataset was collected for the purpose of training and evaluating speaker recognition models. Samples were obtained from non-native English speakers from the arab region over the course of two months. The performed experiments showed that using the developed methodology and the collected dataset, a 94% identification accuracy can be achieved.