Back to Search
Start Over
Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication.
- Source :
-
Entropy . Aug2018, Vol. 20 Issue 8, p600. 1p. - Publication Year :
- 2018
-
Abstract
- 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 (<italic>EER</italic>) and improve the accuracy of voice authentication system in clean and noisy environment. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10994300
- Volume :
- 20
- Issue :
- 8
- Database :
- Academic Search Index
- Journal :
- Entropy
- Publication Type :
- Academic Journal
- Accession number :
- 131555813
- Full Text :
- https://doi.org/10.3390/e20080600