AI 中文总结
该研究针对关键词检索问题提出无乘法的next iRDT特征提取器，在Google KWS 12类数据集上获94.7%验证准确率，处理时间远短于MFCC，适合超低功耗边缘设备。
AI 中文摘要
针对关键词检索（KWS）问题，提出并评估了一种名为next iRDT的极低复杂度特征提取器。与包括广泛使用的MFCC或基于自适应CNN的特征提取器在内的其他类型特征提取器不同，该算法是无乘法的，仅采用简单、节能的算术运算符。由于语音命令关键词检索（KWS）是TinyML平台的典型应用，要求信号分类链具有低复杂度，因此将其作为案例研究来评估复杂度和功能性能。若进行适当调优，iRDT在Google的KWS 12类数据集上，采用基线分类器时表现出与基于MFCC或基于CNN的提取器的解决方案相似的准确率；采用不同分类器时，该系统达到94.7%的验证准确率。所提特征提取器在CPU上的处理时间至少比MFCC小一个数量级，且硬件占用空间极小，非常适合超低功耗边缘设备，代码和演示可获取[18]。
英文摘要
A very low complexity feature extractor called next iRDT is proposed and evaluated for the problem of keyword spotting (KWS). Unlike any other types of feature extractors including the widely used MFCC, or adaptive, CNN-based ones, our algorithm is multiplier-free and it employs only simple, energy-efficient arithmetic operators. Since keyword-spotting of speech commands (KWS) is a typical application for TinyML platforms requiring low complexity for the signal classification chain, we consider it as a case study to evaluate complexity and functional performance. If properly tuned, iRDT demonstrates similar accuracy to solutions based on MFCC or CNN-based extractors using baseline classifiers on Google's KWS 12-classes dataset. With a different classifier the system achieved 94.7% validation accuracy. Processing times on CPU for the proposed feature extractor, are at least one order of magnitude smaller than for the MFCC. The proposed algorithm has a very low hardware footprint, making it ideal for ultra-low power edge devices. Code and demo are available [18].
Comments5 pages, 3 figures, 2 tables, 1 algorithm, submitted to IEEE Signal Processing Letters
