Speaker Recognition Based on Multi-Features Fused by Deep Learning and Kernel Canonical Correlation Analysis
BU Yu
LU lulu
Abstract：The method of speaker recognition based on multi-features fused by deep learning and kernel canonical correlation analysis is proposed in this paper. To acquire two biological features of different modes,deep belief network and convolutional neu?ral network are used to respectively process the audio information and the video information of speaker in parallel. This two non-lin?ear correlated features are fused in feature level by kernel canonical correlation analysis method,the correlation discriminant func?tion is used to extract several pairs of canonical correlation variables whose correlation decrease sequentially but not correlated to each other to constitute the final discriminant feature as the given fusion strategy,which removes redundant information at the same time. At last,the fused feature generated by the kernel correlation analysis method is input into the K-nearest neighbor classifier, and the result of speaker recognition is output from the classifier. BANCA database is used to test the method proposed in this pa?per,the result shows that this method can improve the accuracy of speaker recognition significantly.
Keywords：deep belief networkconvolutional neural networkkernel canonical correlation analysisK-Nearest neighbor classifierspeaker recognition
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 2185-2189,2205 )