Study on Gender Identification Based on Audio Recordings Using Gaussian Mixture Model and Mel Frequency Cepstrum Coefficient Technique

Speaker recognition is an ability to identify speaker’s characteristics based from spoken language. The purpose of this study gender speakers on audio recordings. objective evaluate the accuracy rate technique differentiate and also determine performance classify even when using self-acquired Audio forensics uses voice recordings as part evidence solve cases. This mainly conducted provide easier unknown speaker in forensic field. experiment fulfilled by training pattern classifier dependent data. In order train model, a speech database obtained online corpus comprising both male female speakers. During testing phase, apart data corpus, UTM students will too be used identification experiment. As for run experiment, Mel Frequency Cepstrum Coefficient (MFCC) algorithm extract features while Gaussian Mixture Model (GMM) model identifier. Noise removal was not any Python software MFCC coefficients behavior GMM technique. Experiment results show that GMM-MFCC can regardless language but with varying rate.