Voice Recognition Security Reliability Analysis Using Deep Learning Convolutional Neural Network Algorithm

This study discusses the reliability analysis of voice recognition security using deep learning convolutional neural network (CNN) algorithm. The CNN algorithm has advantages in that it is safer, faster, and more accurate. also can solve user identification problems large amounts data. measured input ten types user's with number iterations 6000, 12000, 15000 sound files. Furthermore, extraction features are performed to recognize conversations retain information very much needed. After that, file iteration data trained register so a model obtained. These results measure performance (confusion matrix) analyze actual value compared predicted obtained best accuracy at iterations, 96.87%, 12000 get 96.30%, 6000 95.77%. CNN's shows files produce high accuracy. Voice helps provide maintain privacy one's identity.