Low-Resource Audio Codec (LRAC): 2025 Challenge Description
Kamil Wojcicki, Yusuf Ziya Isik, Laura Lechler, Mansur Yesilbursa, Ivana Balić, Wolfgang Mack, Rafał Łaganowski, Guoqing Zhang, Yossi Adi, Minje Kim, Shinji Watanabe
TL;DR
The paper introduces the 2025 Low-Resource Audio Codec (LRAC) Challenge, designed to benchmark neural and hybrid speech codecs under joint resource constraints suitable for edge deployment, including compute, bitrate, and latency, with a focus on robustness to noise and reverberation and integration with speech enhancement. It presents a dual-track framework (Track 1: transparent coding under mild distortions; Track 2: enhancement-enabled coding) and provides standardized training data, baselines, and a crowdsourced evaluation pipeline that spans open and blind test sets. The data workflow combines a meticulously curated 702.7 hours of clean speech with diverse noise and reverberation data, plus synthetic and real-world test conditions to reflect real-world scenarios. Final results and methodology aim to inform practical codec design and downstream audio tasks, with future work outlined to expand scope and analysis.
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.