RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features

TL;DR

This paper introduces RNNoise-Ex, a hybrid speech enhancement system that combines RNN and spectral features, improving noise suppression by integrating deep learning with traditional signal processing.

Contribution

It extends the RNNoise system by incorporating additional spectral features during training, enhancing its denoising capabilities.

Findings

Improved noise suppression performance over the original RNNoise.

Effective integration of spectral features with RNNs.

Demonstrated benefits through comparative evaluation.

Abstract

Recent interest in exploiting Deep Learning techniques for Noise Suppression, has led to the creation of Hybrid Denoising Systems that combine classic Signal Processing with Deep Learning. In this paper, we concentrated our efforts on extending the RNNoise denoising system (arXiv:1709.08243) with the inclusion of complementary features during the training phase. We present a comprehensive explanation of the set-up process of a modified system and present the comparative results derived from a performance evaluation analysis, using a reference version of RNNoise as control.