Recently, deep neural networks (DNN) have been widely used in speaker recognition area. In order to achieve fast response time and high accuracy, the requirements for hardware resources increase rapidly. However, as the speaker recognition application is often implemented on mobile devices, it is necessary to maintain a low computational cost while keeping high accuracy in far-field condition. In this paper, we apply structural sparsification on time-delay neural networks (TDNN) to remove redundant structures and accelerate the execution. On our targeted hardware, our model can remove 60% of parameters and only slightly increasing equal error rate (EER) by 0.18% while our structural sparse model can achieve more than 1.5x speedup.
@article{arxiv.1910.11488,
title = {Structural sparsification for Far-field Speaker Recognition with GNA},
author = {Jingchi Zhang and Jonathan Huang and Michael Deisher and Hai Li and Yiran Chen},
journal= {arXiv preprint arXiv:1910.11488},
year = {2020}
}