Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems
This enables reliable on-device speech recognition for battery-powered IoT nodes and hands-free interfaces, though it is incremental as it builds on existing methods for low-resource constraints.
The paper tackled speech command recognition for embedded systems by combining voice activity detection, optimized MFCC features, and a LogNNet reservoir-computing classifier, achieving 92.04% accuracy on a downsampled dataset and validating real-time performance on an Arduino with 90% accuracy using only 18 KB RAM.
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 -> MFCC -> 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.