Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks
Human voice contains characteristics such as: ethnicity, gender, feelings, age and other information, and speaker recognition identifies people based on their voice. Although researchers have worked in this area over the years and provide methods to improve the speaker recognition accuracy, there ar...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Semnan University
2023-03-01
|
| Series: | مجله مدل سازی در مهندسی |
| Subjects: | |
| Online Access: | https://modelling.semnan.ac.ir/article_7302_c39012521bb41c7d63616dbfc6768d78.pdf |
| _version_ | 1797296471078338560 |
|---|---|
| author | Abdolreza Rashno Sadegh Fadaei Abdolsamad Hamidi |
| author_facet | Abdolreza Rashno Sadegh Fadaei Abdolsamad Hamidi |
| author_sort | Abdolreza Rashno |
| collection | DOAJ |
| description | Human voice contains characteristics such as: ethnicity, gender, feelings, age and other information, and speaker recognition identifies people based on their voice. Although researchers have worked in this area over the years and provide methods to improve the speaker recognition accuracy, there are still challenges. In this paper, a new speaker recognition method is proposed based on Gabor filter bank and convolutional neural networks. At first, spectrogram of the speech signal is formed and then, effective Gabor filter bank is designed so that these filters are suitable for extracting effective features of the speech signal. In the next step, spectrogram of the signal is passed through the Gabor filter bank to extract the speech signal features. Finally, speaker recognition is done using a convolutional neural network. Two datasets Aurora2 and TIMIT are used to evaluate the proposed method. Results show that the accuracy of the proposed method is competitive with the state-of-the-art methods. |
| first_indexed | 2024-03-07T22:05:14Z |
| format | Article |
| id | doaj.art-68e70029ed754bee9247223d3316badd |
| institution | Directory Open Access Journal |
| issn | 2008-4854 2783-2538 |
| language | fas |
| last_indexed | 2024-03-07T22:05:14Z |
| publishDate | 2023-03-01 |
| publisher | Semnan University |
| record_format | Article |
| series | مجله مدل سازی در مهندسی |
| spelling | doaj.art-68e70029ed754bee9247223d3316badd2024-02-23T19:10:30ZfasSemnan Universityمجله مدل سازی در مهندسی2008-48542783-25382023-03-012172496710.22075/jme.2022.26690.22457302Automatic Speaker Recognition based on Gabor Features and Convolutional Neural NetworksAbdolreza Rashno0Sadegh Fadaei1Abdolsamad Hamidi2Department of Computer Engineering, Engineering Faculty, Lorestan University, Khorramabad, IranDepartment of Electrical Engineering, Faculty of Engineering, Yasouj University, Yasouj, IranDepartment of Electrical Engineering, Engineering Faculty, Lorestan University, Khorramabad, IranHuman voice contains characteristics such as: ethnicity, gender, feelings, age and other information, and speaker recognition identifies people based on their voice. Although researchers have worked in this area over the years and provide methods to improve the speaker recognition accuracy, there are still challenges. In this paper, a new speaker recognition method is proposed based on Gabor filter bank and convolutional neural networks. At first, spectrogram of the speech signal is formed and then, effective Gabor filter bank is designed so that these filters are suitable for extracting effective features of the speech signal. In the next step, spectrogram of the signal is passed through the Gabor filter bank to extract the speech signal features. Finally, speaker recognition is done using a convolutional neural network. Two datasets Aurora2 and TIMIT are used to evaluate the proposed method. Results show that the accuracy of the proposed method is competitive with the state-of-the-art methods.https://modelling.semnan.ac.ir/article_7302_c39012521bb41c7d63616dbfc6768d78.pdfgabor filter bankspectrogramspeaker recognitionconvolutional neural networks |
| spellingShingle | Abdolreza Rashno Sadegh Fadaei Abdolsamad Hamidi Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks مجله مدل سازی در مهندسی gabor filter bank spectrogram speaker recognition convolutional neural networks |
| title | Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks |
| title_full | Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks |
| title_fullStr | Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks |
| title_full_unstemmed | Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks |
| title_short | Automatic Speaker Recognition based on Gabor Features and Convolutional Neural Networks |
| title_sort | automatic speaker recognition based on gabor features and convolutional neural networks |
| topic | gabor filter bank spectrogram speaker recognition convolutional neural networks |
| url | https://modelling.semnan.ac.ir/article_7302_c39012521bb41c7d63616dbfc6768d78.pdf |
| work_keys_str_mv | AT abdolrezarashno automaticspeakerrecognitionbasedongaborfeaturesandconvolutionalneuralnetworks AT sadeghfadaei automaticspeakerrecognitionbasedongaborfeaturesandconvolutionalneuralnetworks AT abdolsamadhamidi automaticspeakerrecognitionbasedongaborfeaturesandconvolutionalneuralnetworks |