# Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation

## TL;DR

This paper introduces a deep subband filtering approach that extends neural network-based masking for speech dereverberation, outperforming traditional masking while maintaining similar denoising performance, with minimal additional computational cost.

## Contribution

It extends deep neural network masks to deep subband filters, improving dereverberation performance by aligning with subband approximation assumptions.

## Key findings

- Deep subband filtering outperforms multiplicative masking for dereverberation.
- The method requires minimal additional parameters and computational overhead.
- Denoising performance remains virtually unchanged.

## Abstract

In this paper, we present a scheme for extending deep neural network-based multiplicative maskers to deep subband filters for speech restoration in the time-frequency domain. The resulting method can be generically applied to any deep neural network providing masks in the time-frequency domain, while requiring only few more trainable parameters and a computational overhead that is negligible for state-of-the-art neural networks. We demonstrate that the resulting deep subband filtering scheme outperforms multiplicative masking for dereverberation, while leaving the denoising performance virtually the same. We argue that this is because deep subband filtering in the time-frequency domain fits the subband approximation often assumed in the dereverberation literature, whereas multiplicative masking corresponds to the narrowband approximation generally employed for denoising.