A Speech Enhancement Method Using Fast Fourier Transform and Convolutional Autoencoder

TL;DR

This paper introduces a lightweight speech enhancement method combining FFT and convolutional autoencoders, demonstrating competitive results in a speech reconstruction challenge without relying on neural networks.

Contribution

The paper presents a novel hybrid approach using FFT and convolutional autoencoders for speech enhancement, achieving high performance in a competitive setting.

Findings

Achieved second place in Helsinki Speech Challenge 2024

Demonstrated effectiveness of neural-network-free methods

Showed potential of FFT-ConvAE for speech reconstruction

Abstract

This paper addresses the reconstruction of audio signals from degraded measurements. We propose a lightweight model that combines the discrete Fourier transform with a Convolutional Autoencoder (FFT-ConvAE), which enabled our team to achieve second place in the Helsinki Speech Challenge 2024. Our results, together with those of other teams, demonstrate the potential of neural-network-free approaches for effective speech signal reconstruction.