Technical Program
Last updated: 9 Apr 2026
See the Agenda for the full schedule including breaks and evening event.
Keynotes
| Time | Speaker | Title |
|---|---|---|
| 09:10 – 09:55 | Jean-Marc Valin (Google) | From Paper to Production: the Engineering and Standardization Challenges of Neural Speech Coding |
| 11:30 – 12:15 | Nicola Pia (Fraunhofer IIS) | Design Choices and Effective Evaluation of Modern Speech and Audio Codecs Based on Neural Networks |
| 16:15 – 17:00 | Cullen Jennings (Cisco Systems) | More Bandwidth, More Problems: Audio Codecs in the Machine Learning Era |
Oral Presentations
10:00 – 10:20 · 20 min · Challenge overview talk by the challenge organizers.
10:20 – 11:00 · 40 min · Presentations by the respective winners of each LRAC Challenge track.
| Paper ID | Title | Authors |
|---|---|---|
| LRAC-AS-18745 | IRIS: Low-Complexity High-Efficiency Neural Network Codec for Real-Time Audio Transmission | Ziqian Wu, Jiawei Jiang, Kunpeng Lin, He Wang, Qingbo Huang, Dejun Zhang, Andong Li |
| LRAC-AS-18770 | Progressive Refinement Training for Low-Resource Neural Speech Coding and Enhancement | Ronghui Hu, Leyan Yang, Yang Xu, Qinwen Hu, Jing Lu |
Poster Session
14:15 – 15:45 · 90 min · Authors free to roam after 60 min.
PA1–3 are Archival Track (ICASSPW). PA4 is Non-Archival Track.
PA1. LRAC Challenge Entries
| Paper ID | Title | Authors |
|---|---|---|
| LRAC-AS-18745 | IRIS: Low-Complexity High-Efficiency Neural Network Codec for Real-Time Audio Transmission | Ziqian Wu, Jiawei Jiang, Kunpeng Lin, He Wang, Qingbo Huang, Dejun Zhang, Andong Li |
| LRAC-AS-18770 | Progressive Refinement Training for Low-Resource Neural Speech Coding and Enhancement | Ronghui Hu, Leyan Yang, Yang Xu, Qinwen Hu, Jing Lu |
| LRAC-AS-18771 | KD-Vocodec: A Low-Complexity Model for Joint Speech Coding and Enhancement Using Knowledge Distillation | Yang Xu, Ronghui Hu, Leyan Yang, Jing Lu |
| LRAC-AS-18772 | VOCODEC: An Efficient Lightweight Low-Bitrate Speech Codec | Leyan Yang, Ronghui Hu, Yang Xu, Jing Lu |
| LRAC-AS-18785 | Nanocodec: Towards Low Bitrate and Low Complexity Real-Time Neural Audio Codec | Andong Li, Linping Xu, Zhe Han, Lingling Dai, Yiqing Guo, Hua Gao, Xiaodong Li, Chengshi Zheng |
| LRAC-AS-18800 | PHOENIXCODEC: Taming Neural Speech Coding For Extreme Low-Resource Scenarios | Zixiang Wan, Haoran Zhao, Guochang Zhang, Runqiang Han, Jianqiang Wei, Yuexian Zou |
PA2. LRAC Challenge Design and Outcomes
| Paper ID | Title | Authors |
|---|---|---|
| LRAC-AS-18778 | Low-Resource Audio Codec (LRAC): 2025 Challenge Description | Kamil Wojcicki, Yusuf Isik, Laura Lechler, Mansur Yesilbursa, Ivana Balić, Wolfgang Mack, Rafał Łaganowski, Guoqing Zhang, Yossi Adi, Minje Kim |
PA3. Broader Impacts and Applications
| Paper ID | Title | Authors |
|---|---|---|
| LRAC-AS-18780 | Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations | Ryo Aihara, Yoshiki Masuyama, François Germain, Gordon Wichern, Jonathan Le Roux |
| LRAC-AS-18807 | Attention-Guided Audio Compression for Multimodal LLMs | Prerana Rane, Amitesh Vatsa, Yash Pethe, Ogan Batu Aktolun, Kevin Li, Ishan Singh |
PA4. Non-Archival Track
| Paper ID | Title | Authors |
|---|---|---|
| LRAC-NAS-1 | Personalized Low-Bitrate Coded Speech Restoration Via Embedding Conditioning And Cluster-Based Model Selection | Eray Özgünay, Christian Rollwage, Jan Rennies, Xavier Domont, Mattes Ohlenbusch, Simon Doclo |
| LRAC-NAS-2 | How Training Data Affects Speech-Enhancing Neural Codecs: A Data-Centric Study Under Low-Bitrate Constraints | S.A. Raczyński and E. Gómez and K. Główczewski and M. Olszewski and K. Duzinkiewicz and M. Kraiński |
Panel Discussion
May 4, 2026 · 17:00 – 18:00 · 60 min
| Topic | Are Neural Codecs Ready for Low-Resource Reality? Potentials and Pitfalls in the AI Era. |
| Host | Minje Kim |
| Panelists | Yossi Adi, Nicola Pia, Jean-Marc Valin, and Cullen Jennings |