Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.19205956 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>This repository is intended to reproduce and run experiments for a FPGA implementation of event-based audio data processing system for spoken word classification.<br>The system employs an <strong>event-by-event processing</strong> approach using graph neural networks. The weights provided in the project enable processing of spoken digits and were obtained through training on the Spiking Heidelberg Digits Dataset (SHD).</p> <p>The repository includes all necessary hardware modules (SystemVerilog RTL files), along with the required IP cores and memory initialization files.</p> <p>The data and implementation are associated with the following publication:</p> <p><strong>Hardware-accelerated event-graph neural networks for low-latency time-series classification on SoC FPGA</strong><br>Hiroshi Nakano, Krzysztof Błachut, Kamil Jeziorek, Piotr Wzorek, Manon Dampfhoffer, Thomas Mesquida, Hiroaki Nishi, Tomasz Kryjak, Thomas Dalgaty.</p> <p>In: Applied Reconfigurable Computing: Architectures, Tools, and Applications – ARC 2025 Proceedings,<br>21st International Symposium, ARC 2025 – Applied Reconfigurable Computing,<br>Seville, Spain, April 9–11, 2025.<br>Published by Springer in the Lecture Notes in Computer Science (LNCS 15594), pp. 51–68.<br>ISBN: 978-3-031-87994-4, eISBN: 978-3-031-87995-1.</p> <p> </p> <p>This work was supported by the Polish National Science Centre project 2024/53/N/ST6/04331.</p>