A novel speech feature fusion algorithm for text-independent speaker recognition

• Published in: Multimedia tools and applications Vol. 83; no. 24; pp. 64139 - 64156
• Main Authors: Ma, Biao, Xu, Chengben, Zhang, Ye
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2024; Springer Nature B.V
• Subjects: Algorithms; Artificial neural networks; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Feature extraction; Matrices (mathematics); Multimedia Information Systems; Special Purpose and Application-Based Systems; Speech; Speech recognition; Tensors; Vector analysis; Feature fusion; Speaker recognition; Independent vector analysis; Parallel neural network
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-18077-9

A novel speech feature fusion algorithm with independent vector analysis (IVA) and parallel convolutional neural network (PCNN) is proposed for text-independent speaker recognition. Firstly, some different feature types, such as the time domain (TD) features and the frequency domain (FD) features, can be extracted from a speaker’s speech. Generally, the TD and the FD features can be considered as the linear mixtures of independent feature components (IFCs) with an unknown mixing system. To estimate the IFCs, the TD and the FD features of the speaker’s speech are concatenated to build the TD and the FD feature matrix, respectively, and then a feature tensor of the speaker’s speech is obtained by paralleling the TD and the FD feature matrix. The IVA can be used to estimate the IFC matrices of TD and FD features with the feature tensor. The IFC matrices are utilized as the input of the PCNN to extract the deep features of the TD and FD features, respectively. Finally, the deep features can be integrated to obtain the fusion feature of the speaker’s speech for speaker recognition. The experimental results show the effectiveness and performances of the proposed speaker recognition system.