Image to Image Translation based on Convolutional Neural Network Approach for Speech Declipping

TL;DR

This paper introduces a U-Net based convolutional neural network approach for speech declipping, translating magnitude spectrum images of clipped speech into clean speech images, improving quality and intelligibility especially under severe clipping and noise conditions.

Contribution

The paper presents a novel image-to-image translation method using U-Net for speech declipping, outperforming existing methods in quality and robustness.

Findings

Outperforms other declipping methods in quality and intelligibility

Effective in severe clipping scenarios

Maintains performance under additive Gaussian noise

Abstract

Clipping, as a current nonlinear distortion, often occurs due to the limited dynamic range of audio recorders. It degrades the speech quality and intelligibility and adversely affects the performances of speech and speaker recognitions. In this paper, we focus on enhancement of clipped speech by using a fully convolutional neural network as U-Net. Motivated by the idea of image-to-image translation, we propose a declipping approach, namely U-Net declipper in which the magnitude spectrum images of clipped signals are translated to the corresponding images of clean ones. The experimental results show that the proposed approach outperforms other declipping methods in terms of both quality and intelligibility measures, especially in severe clipping cases. Moreover, the superior performance of the U-Net declipper over the well-known declipping methods is verified in additive Gaussian noise conditions.