Low-Resource Audio Codec (LRAC): 2025 Challenge Description

TL;DR

This paper introduces the 2025 Low-Resource Audio Codec Challenge to promote development of neural and hybrid codecs optimized for resource-constrained environments, addressing robustness, low latency, and practical deployment issues.

Contribution

It establishes a standardized benchmark, dataset, and evaluation framework to accelerate research in low-resource neural audio codecs and their robustness to acoustic distortions.

Findings

Baseline systems provided for comparison

Standardized dataset enables fair benchmarking

Expected insights into resource-efficient codec design

Abstract

While recent neural audio codecs deliver superior speech quality at ultralow bitrates over traditional methods, their practical adoption is hindered by obstacles related to low-resource operation and robustness to acoustic distortions. Edge deployment scenarios demand codecs that operate under stringent compute constraints while maintaining low latency and bitrate. The presence of background noise and reverberation further necessitates designs that are resilient to such degradations. The performance of neural codecs under these constraints and their integration with speech enhancement remain largely unaddressed. To catalyze progress in this area, we introduce the 2025 Low-Resource Audio Codec Challenge, which targets the development of neural and hybrid codecs for resource-constrained applications. Participants are supported with a standardized training dataset, two baseline systems, and a comprehensive evaluation framework. The challenge is expected to yield valuable insights applicable to both codec design and related downstream audio tasks.