Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks
Machine Learning
2019-04-03 v1 Sound
Audio and Speech Processing
Machine Learning
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.
Keywords
Cite
@article{arxiv.1904.01269,
title = {Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks},
author = {Stefano Imoscopi and Volodya Grancharov and Sigurdur Sverrisson and Erlendur Karlsson and Harald Pobloth},
journal= {arXiv preprint arXiv:1904.01269},
year = {2019}
}