papers AI Learner
The Github is limit! Click to go to the new site.

Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks

2019-04-02
Stefano Imoscopi, Volodya Grancharov, Sigurdur Sverrisson, Erlendur Karlsson, Harald Pobloth

Abstract

This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.01269

PDF

http://arxiv.org/pdf/1904.01269


Comments

Content