The recognition of gender voices as an important part of answering certain voices. To distinguish gender from sound signals, sound techniques have defined the gender-relevant features (male or female) of these sound signals. In this study, we used various models to improve accuracy, one of which was by using deep learning with the voice gender DNN method. This noise reduction uses the extraction feature of the Mel Frequency Cepstral Coefficient (MFCC), then the sound classification uses SVM. By using a separation ratio of 80% for training data and 20% for testing data. The results showed that using DNN for voice recognition was better and pairing with the SVM algorithm obtained an accurate result of 0.97%.

Keywords : Voice Recognition, Deep Neural Network, Deep Learning, MFCC, SVM.