Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks

TL;DR

This paper introduces a high-fidelity GAN-based method for speech bandwidth expansion that is trained end-to-end and can generalize to unseen bandwidth factors, significantly improving speech quality in digital applications.

Contribution

The paper presents the first end-to-end GAN model capable of zero-shot speech bandwidth expansion across multiple ratios, outperforming previous methods.

Findings

Outperforms previous end-to-end approaches in speech quality.

Demonstrates zero-shot generalization to unseen bandwidth ratios.

Effective in practical speech enhancement applications.

Abstract

Speech bandwidth expansion is crucial for expanding the frequency range of low-bandwidth speech signals, thereby improving audio quality, clarity and perceptibility in digital applications. Its applications span telephony, compression, text-to-speech synthesis, and speech recognition. This paper presents a novel approach using a high-fidelity generative adversarial network, unlike cascaded systems, our system is trained end-to-end on paired narrowband and wideband speech signals. Our method integrates various bandwidth upsampling ratios into a single unified model specifically designed for speech bandwidth expansion applications. Our approach exhibits robust performance across various bandwidth expansion factors, including those not encountered during training, demonstrating zero-shot capability. To the best of our knowledge, this is the first work to showcase this capability. The experimental results demonstrate that our method outperforms previous end-to-end approaches, as well as interpolation and traditional techniques, showcasing its effectiveness in practical speech enhancement applications.