The 2026 LRAC Workshop

An ICASSP 2026 Satellite Workshop

Table of Contents

1. Call for Papers
2. Motivation
3. Aims

Call for Papers

We invite you to submit your work to the 2026 Low-Resource Audio Codec (LRAC) Workshop an exciting opportunity to advance the state-of-the-art in neural audio coding for resource-constrained devices. This inaugural edition of the workshop brings together researchers and practitioners to advance neural speech coding for resource-constrained devices. The central theme is developing low-resource, efficient neural speech codecs that are lightweight, suitable for real-world deployment, and effective under everyday noise and reverberation conditions. We welcome submissions that explore diverse application scenarios and system requirements, provided they maintain a strong connection to our core focus on efficient codecs for real-world environments.

Workshop details at a glance:

• Topics: https://lrac.short.gy/workshop-topics
• Tracks: https://lrac.short.gy/workshop-tracks
• Archival track paper deadline: October 22, 2025
• Non-archival track paper deadline: February 7, 2026
• Workshop date: May 4, 2026
• Workshop location: Barcelona, Spain (satellite to ICASSP 2026)

See the PDF version of the Call for Papers: LRAC-Workshop-Call-for-Papers.pdf

Back to top

Motivation

The growing demand for speech interfaces across a wide range of resource-constrained environments—including general-purpose computing platforms with limited processing or power budgets, embedded systems, and mobile devices—requires speech codecs for real-time communication that are efficient in terms of compute, bitrate, and latency, while also delivering high-quality speech under real-world conditions. Although recent neural coding methods excel at optimizing for these constraints individually, addressing all three simultaneously remains an open challenge.

Back to top

Aims

The first edition of the LRAC Workshop is dedicated to bridging this gap and advancing the state of the art in speech codecs under joint resource constraints. We especially encourage research addressing performance in realistic noise and reverberation environments.

The objectives of the 2026 LRAC Workshop are to:

1. Drive advances in state-of-the-art low-resource low-bitrate speech coding methods.

2. Highlight challenges in creating efficient codecs under practical constraints.

3. Foster collaboration and discussion across academia and industry.

4. Encourage development and benchmarking under real-world acoustic conditions.

Back to top