A Multiscale Chaotic Feature Extraction Method for Speaker Recognition. (3rd December 2020)

• Record Type: Journal Article
• Authors: Lin, Jiang; Yumei, Yi; Maosheng, Zhang; Defeng, Chen; Chao, Wang; Tonghan, Wang
• Other Names: Rajagopal Karthikeyan Academic Editor.
• Is Part Of: Complexity. Volume 2020(2020)
• Publication Date: 2020-12-03
• Subjects: Chaotic behavior in systems -- Periodicals; Complexity (Philosophy) -- Periodicals; 003
• DOI: 10.1155/2020/8810901
• Languages: English
• ISSNs: 1076-2787

Abstract

Abstract : In speaker recognition systems, feature extraction is a challenging task under environment noise conditions. To improve the robustness of the feature, we proposed a multiscale chaotic feature for speaker recognition. We use a multiresolution analysis technique to capture more finer information on different speakers in the frequency domain. Then, we extracted the speech chaotic characteristics based on the nonlinear dynamic model, which helps to improve the discrimination of features. Finally, we use a GMM-UBM model to develop a speaker recognition system. Our experimental results verified its good performance. Under clean speech and noise speech conditions, the ERR value of our method is reduced by 13.94% and 26.5% compared with the state-of-the-art method, respectively.