Speaker Identification Based Proxy Attendance Detection System
Naman Gupta, Shikha Jain · 2019
Recently, voice biometrics has gained popularity due to its large number of applications. The paper presents Siamese Network and CIFAR network-based architecture for speaker identification. It uses the voice metrics and voice features independent of the uttered words. The model is trained on a dataset containing hundreds of audio clips of 10 speakers. The model achieved a test accuracy of 88% and training accuracy of 98.5%. The proposed model is used for proxy attendance detection in the classroom.