Memristive Nanowire Network for Energy Efficient Audio Classification: Pre-Processing-Free Reservoir Computing with Reduced Latency

Akshaya Rajesh, Pavithra Ananthasubramanian, Nagarajan Raghavan +1

Efficient audio feature extraction is critical for low-latency, resource-constrained speech recognition. Conventional preprocessing techniques, such as Mel Spectrogram, Perceptual…