A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
Jiang Lin,
Yi Yumei,
Zhang Maosheng,
Chen Defeng,
Wang Chao,
Wang Tonghan
Affiliations
Jiang Lin
College of Computer and Information Engineering, Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, China
Yi Yumei
College of Computer and Information Engineering, Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, China
Zhang Maosheng
School of Mathematics and Statistics, Yulin Normal University, Yulin 537000, China
Chen Defeng
College of Computer and Information Engineering, Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, China
Wang Chao
National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan 430072, China
Wang Tonghan
School of Software, East China University of Technology, Nanchang 330013, China
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.
