Speaker Recognition System based on CNN for Intelligent Attendance

Abstract

With the rapid development of information technology, student attendance has changed from using paper to using machine, such as taking photos, scanning QR codes, positioning, etc. These attendance work needs to turn on camera to take photos, which is slightly inefficient, or turn on the positioning service. However, many people think that turning on the positioning service will infringe on personal privacy. Therefore, we need to consider a more efficient attendance method that does not infringe on personal privacy. Voice, a signal which can be quickly obtained and contain a variety of information, can be used for class students' attendance. This paper studies, designs and implements a voiceprint recognition system based on convolutional neural networks (CNN), which can effectively recognize specific speakers. The speaker recognition system based on CNN constructed in this paper. The system mainly includes three steps: voiceprint registration stage, data training stage and speaker online recognition stage.