{"ID":2876256,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00862","arxiv_id":"2509.00862","title":"Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems","abstract":"This paper presents a low-resource speech-command recognizer combining energy-based voice activity detection (VAD), an optimized Mel-Frequency Cepstral Coefficients (MFCC) pipeline, and the LogNNet reservoir-computing classifier. Using four commands from the Speech Commands da-taset downsampled to 8 kHz, we evaluate four MFCC aggregation schemes and find that adaptive binning (64-dimensional feature vector) offers the best accuracy-to-compactness trade-off. The LogNNet classifier with architecture 64:33:9:4 reaches 92.04% accuracy under speaker-independent evaluation, while requiring significantly fewer parameters than conventional deep learn-ing models. Hardware implementation on Arduino Nano 33 IoT (ARM Cor-tex-M0+, 48 MHz, 32 KB RAM) validates the practical feasibility, achieving ~90% real-time recognition accuracy while consuming only 18 KB RAM (55% utilization). The complete pipeline (VAD -\u003e MFCC -\u003e LogNNet) thus enables reliable on-device speech-command recognition under strict memory and compute limits, making it suitable for battery-powered IoT nodes, wire-less sensor networks, and hands-free control interfaces.","short_abstract":"This paper presents a low-resource speech-command recognizer combining energy-based voice activity detection (VAD), an optimized Mel-Frequency Cepstral Coefficients (MFCC) pipeline, and the LogNNet reservoir-computing classifier. Using four commands from the Speech Commands da-taset downsampled to 8 kHz, we evaluate fo...","url_abs":"https://arxiv.org/abs/2509.00862","url_pdf":"https://arxiv.org/pdf/2509.00862v1","authors":"[\"Yuriy Izotov\",\"Andrei Velichko\"]","published":"2025-08-31T14:16:09Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"cs.LG\",\"eess.AS\"]","methods":"[\"Graph Neural Network\"]","has_code":false}