提出无乘法运算的低复杂度特征提取器，适合边缘设备关键词识别。
A Multiplication-Free Feature Extractor for Signal Classification: Keyword Spotting Case Study
- 采用仅含简单算术运算的无乘法设计，降低计算开销。
- 在12类关键词数据集上达94.7%验证准确率，接近MFCC与CNN性能。
- 处理速度比MFCC快一个数量级，适合超低功耗嵌入式设备。
提出一种名为next iRDT的极低复杂度特征提取器，用于关键词识别（KWS）任务。与广泛使用的MFCC或基于CNN的自适应提取器不同，该算法完全避免乘法运算，仅使用简单的能量高效算术操作。鉴于语音命令的关键词识别是典型适用于TinyML平台、要求信号分类链低复杂度的应用场景，本文以此为案例评估其复杂度与功能表现。经适当调优后，iRDT在谷歌的KWS 12-类数据集上，使用基线分类器时达到与基于MFCC或CNN的方案相当的准确率；采用另一分类器时系统获得94.7%的验证准确率。在CPU上的处理时间比MFCC至少快一个数量级。所提算法具有极小的硬件占用，非常适合超低功耗边缘设备。代码与演示已公开。
原文摘要 · Abstract (English)
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].
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。