Discriminative autoencoders for speaker verification.
ICASSP, pp.5375-5379, (2017)
This paper presents a learning and scoring framework based on neural networks for speaker verification. The framework employs an autoencoder as its primary structure while three factors are jointly considered in the objective function for speaker discrimination. The first one, relating to the sample reconstruction error, makes the structu...More
Full Text (Upload PDF)
PPT (Upload PPT)