Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement

TL;DR

This paper introduces a hybrid denoising network that combines temporal and frequency domain features to enhance speech quality by effectively removing diverse noise types, outperforming single-domain models.

Contribution

The paper proposes a novel hybrid framework that integrates raw-audio and spectrogram representations for improved multi-domain speech enhancement.

Findings

Hybrid model outperforms individual domain models in noise removal

Enhanced robustness against various noise types

Improved speech quality metrics in experiments

Abstract

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific representations such as raw-audio and spectrograms are each effective at targeting different types of noise. By integrating both approaches, our model can learn multi-scale and multi-domain features, effectively removing noise existing on different regions on the time-frequency space in a complementary way. Experimental results show that the proposed hybrid model yields better performance and robustness than using each model individually.