We study the role of magnitude structured pruning as an architecture search to speed up the inference time of a deep noise suppression (DNS) model. While deep learning approaches have been remarkably successful in enhancing audio quality, their increased complexity inhibits their deployment in real-time applications. We achieve up to a 7.25X inference speedup over the baseline, with a smooth model performance degradation. Ablation studies indicate that our proposed network re-parameterization (i.e., size per layer) is the major driver of the speedup, and that magnitude structured pruning does comparably to directly training a model in the smaller size. We report inference speed because a parameter reduction does not necessitate speedup, and we measure model quality using an accurate non-intrusive objective speech quality metric.
@article{arxiv.2110.04378,
title = {Performance optimizations on deep noise suppression models},
author = {Jerry Chee and Sebastian Braun and Vishak Gopal and Ross Cutler},
journal= {arXiv preprint arXiv:2110.04378},
year = {2021}
}