Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication
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 sp...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/20/8/600 |
| _version_ | 1798040205489340416 |
|---|---|
| author | Lei Lei Kun She |
| author_facet | Lei Lei Kun She |
| author_sort | Lei Lei |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T22:04:14Z |
| format | Article |
| id | doaj.art-7d105d9d0c3c44f69aa1c797b3a6ddb1 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T22:04:14Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-7d105d9d0c3c44f69aa1c797b3a6ddb12022-12-22T04:00:47ZengMDPI AGEntropy1099-43002018-08-0120860010.3390/e20080600e20080600Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice AuthenticationLei Lei0Kun She1School of Information and Software Engineering, University of Electrical and Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Software Engineering, University of Electrical and Science and Technology of China, Chengdu 610054, ChinaRecently, 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.http://www.mdpi.com/1099-4300/20/8/600i-vectorwavelet entropyspeaker authenticationCNN |
| spellingShingle | Lei Lei Kun She Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication Entropy i-vector wavelet entropy speaker authentication CNN |
| title | Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication |
| title_full | Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication |
| title_fullStr | Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication |
| title_full_unstemmed | Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication |
| title_short | Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication |
| title_sort | identity vector extraction by perceptual wavelet packet entropy and convolutional neural network for voice authentication |
| topic | i-vector wavelet entropy speaker authentication CNN |
| url | http://www.mdpi.com/1099-4300/20/8/600 |
| work_keys_str_mv | AT leilei identityvectorextractionbyperceptualwaveletpacketentropyandconvolutionalneuralnetworkforvoiceauthentication AT kunshe identityvectorextractionbyperceptualwaveletpacketentropyandconvolutionalneuralnetworkforvoiceauthentication |