Abstract
The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN, with the primary task of classifying the target speakers and the auxiliary task of reconstructing the higher-order statistics of the original input utterance. The proposed training strategy aggregates both the supervised and unsupervised learning into one framework to make the speaker embeddings more discriminative and robust. Experiments are carried out in the NIST SRE16 evaluation dataset and the VOiCES dataset. The results demonstrate that our proposed method outperform the original x-vector approach with very low additional complexity added.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1903.12058