# Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques

## TL;DR

This paper introduces parameter pruning and quantization techniques to significantly reduce the size of deep learning speech enhancement models while maintaining near-original performance, enabling deployment on resource-limited devices.

## Contribution

It proposes a novel combination of parameter pruning and quantization methods to create highly compact speech enhancement models with minimal performance loss.

## Key findings

- Model size reduced to 10.03% of original
- Minor performance degradation in STOI and PESQ scores
- Techniques suitable for resource-constrained devices

## Abstract

Most recent studies on deep learning based speech enhancement (SE) focused on improving denoising performance. However, successful SE applications require striking a desirable balance between denoising performance and computational cost in real scenarios. In this study, we propose a novel parameter pruning (PP) technique, which removes redundant channels in a neural network. In addition, a parameter quantization (PQ) technique was applied to reduce the size of a neural network by representing weights with fewer cluster centroids. Because the techniques are derived based on different concepts, the PP and PQ can be integrated to provide even more compact SE models. The experimental results show that the PP and PQ techniques produce a compacted SE model with a size of only 10.03% compared to that of the original model, resulting in minor performance losses of 1.43% (from 0.70 to 0.69) for STOI and 3.24% (from 1.85 to 1.79) for PESQ. The promising results suggest that the PP and PQ techniques can be used in a SE system in devices with limited storage and computation resources.