Publication Date:
2018-08-14
Description:
Entropy, Vol. 20, Pages 600: Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication Entropy doi: 10.3390/e20080600 Authors: Lei Lei Kun She Recently, the accuracy of voice authentication system has increased significantly due to the successful application of the identity vector (i-vector) model. This paper proposes a new method for i-vector extraction. In the method, a perceptual wavelet packet transform (PWPT) is designed to convert speech utterances into wavelet entropy feature vectors, and a Convolutional Neural Network (CNN) is designed to estimate the frame posteriors of the wavelet entropy feature vectors. In the end, i-vector is extracted based on those frame posteriors. TIMIT and VoxCeleb speech corpus are used for experiments and the experimental results show that the proposed method can extract appropriate i-vector which reduces the equal error rate (EER) and improve the accuracy of voice authentication system in clean and noisy environment.
Electronic ISSN:
1099-4300
Topics:
Chemistry and Pharmacology
,
Physics
Permalink
