Helsinki Speech Challenge 2024

TL;DR

HSC2024 is a challenge that provides a dataset with corrupted speech recordings to promote the development of advanced deconvolution and speech enhancement techniques, evaluated through speech recognition metrics.

Contribution

The paper introduces a new dataset and challenge focused on deconvolving and enhancing corrupted speech recordings, fostering innovation in speech restoration methods.

Findings

Dataset includes paired clean and corrupted speech samples.

Evaluation uses speech recognition performance as a metric.

Aims to improve real-world speech enhancement techniques.

Abstract

The Helsinki Speech Challenge 2024 (HSC2024) invites researchers to enhance and deconvolve speech audio recordings. We recorded a dataset that challenges participants to apply speech enhancement and inverse problems techniques to recorded speech data. This dataset includes paired samples of AI-generated clean speech and corresponding recordings, which feature varying levels of corruption, including frequency attenuation and reverberation. The challenge focuses on developing innovative deconvolution methods to accurately recover the original audio. The effectiveness of these methods will be quantitatively assessed using a speech recognition model, providing a relevant metric for evaluating enhancements in real-world scenarios.