This paper introduces an innovative method for reducing the computational complexity of deep neural networks in real-time speech enhancement on resource-constrained devices. The proposed approach utilizes a two-stage processing framework, employing channelwise feature reorientation to reduce the computational load of convolutional operations. By combining this with a modified power law compression technique for enhanced perceptual quality, this approach achieves noise suppression performance comparable to state-of-the-art methods with significantly less computational requirements. Notably, our algorithm exhibits 3 to 4 times less computational complexity and memory usage than prior state-of-the-art approaches.
@article{arxiv.2312.08132,
title = {Ultra Low Complexity Deep Learning Based Noise Suppression},
author = {Shrishti Saha Shetu and Soumitro Chakrabarty and Oliver Thiergart and Edwin Mabande},
journal= {arXiv preprint arXiv:2312.08132},
year = {2024}
}