A Kernel Method for Speaker Recognition with Little Data

Abstract

It proposed a fuzzy kernel vector quantization method for speaker recognition with little training data. By non-linear mapping, it quantized the input data in the high-dimensional feature space, and used the cluster centers to form the speaker's model. Because of the kernel method, it made the inherent speech features explored, and the dissimilarity among… (More)

Topics

1 Figure or Table

Slides referencing similar topics