About
Table of Contents
Theme
The LRAC 2.0 Challenge (the 2026 Low-Resource Audio Codec Challenge) 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, while meeting strict constraints on computational complexity, memory, latency, and bitrate, and scaling toward perceptual transparency across languages.

Organizers
- Kamil Wojcicki, Cisco Systems, Australia
- Yusuf Isik, Cisco Systems, Türkiye
- Mansur Yesilbursa, Cisco Systems, Poland
- Ivana Balic, Cisco Systems, Switzerland
- Erfan Loweimi, Cisco Systems, UK
- Anna Bartlett, Cisco Systems, UK
- Rafał Łaganowski, Cisco Systems, Poland
- Nezih Topaloglu, Cisco Systems, Türkiye
Co-Organizers & Academic Partners
- Shinji Watanabe, Carnegie Mellon University, USA
- Minje Kim, University of Illinois Urbana-Champaign, USA
- Yossi Adi, Hebrew University of Jerusalem, Israel
Sponsors
- Speech and Language Processing Technical Committee (IEEE Signal Processing Society)
- Audio and Acoustic Signal Processing Technical Committee (IEEE Signal Processing Society)
Contact Information
Challenge related enquiries can be sent to lrac-challenge@cisco.com.
We are also on Slack - please send us an email to request an invitation link.