Hardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGA

Hardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGA explores Develop a low-power, low-latency hardware-accelerated event-graph neural network for real-time audio classification and keyword spotting on FPGA.. Commercial viability score: 7/10 in Hardware-Accelerated AI.