用轻量级模型实现嵌入式设备上的高精度语音指令识别
Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems
- 结合能量检测与优化的梅尔倒谱系数提取
- 在8kHz采样下达92.04%准确率，仅需18KB内存
- 适合电池供电物联网节点的实时语音控制
本文提出一种低资源语音指令识别系统，结合基于能量的语音活动检测（VAD）、优化的梅尔频率倒谱系数（MFCC）提取流程，以及LogNNet储层计算分类器。在8kHz采样的语音命令数据集上，采用四种MFCC聚合方案，发现自适应分箱（64维特征向量）在准确率与紧凑性间表现最佳。LogNNet分类器（架构64:33:9:4）在无特定说话人评估下达到92.04%准确率，参数量远低于传统深度学习模型。在Arduino Nano 33 IoT（ARM Cortex-M0+，48 MHz，32 KB RAM）上实现，实测识别准确率约90%，仅消耗18 KB RAM（55%利用率）。完整流水线（VAD → MFCC → LogNNet）可在严苛内存与算力限制下实现可靠本地语音识别，适用于电池供电物联网节点、无线传感器网络及免提控制界面。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。