English

Ultra Low Complexity Deep Learning Based Noise Suppression

Audio and Speech Processing 2024-06-10 v1 Machine Learning Signal Processing

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-28T13:49:41.530Z