USTCSpeech System for VOiCES from a Distance Challenge 2019
Audio and Speech Processing
2019-04-01 v1
Abstract
This document describes the speaker verification systems developed in the Speech lab at the University of Science and Technology of China (USTC) for the VOiCES from a Distance Challenge 2019. We develop the system for the Fixed Condition on two public corpus, VoxCeleb and SITW. The frameworks of our systems are based on the mainstream ivector/PLDA and x-vector/PLDA algorithms.
Cite
@article{arxiv.1903.12428,
title = {USTCSpeech System for VOiCES from a Distance Challenge 2019},
author = {Lanhua You and Bin Gu and Wu Guo},
journal= {arXiv preprint arXiv:1903.12428},
year = {2019}
}