Voiceprint recognition check-in system based on deep learning

ABSTRACT

With the development of modern technology and the rise of artificial intelligence, the application scenarios of identity authentication technology are becoming more and more complex, especially in the current situation of the spread of the new coronavirus, traditional identity authentication technology can no longer meet people's practical needs, and society urgently needs a security and convenient authentication technology. Voiceprint recognition is a kind of biometric technology, and it is one of the products of comprehensive research on computer technology, acoustics and life sciences. This paper introduces a voiceprint recognition check-in system based on deep learning algorithm. In this design, the audio is converted into Mel frequency cepstral coefficients, and then the convolution network is provided to extract features. Finally, the similarity is calculated to obtain the classification result for voiceprint feature extraction, which is compared with the voice database data to realize voiceprint recognition. The voiceprint recognition check-in system introduced in this paper has a check-in system with an interactive interface. The average recognition rate of the system measured by experiments is higher than 93.3%, which can meet the requirements of practical applications. © 2022 IEEE.