Efficient audio feature extraction is critical for low-latency, resource-constrained speech recognition. Conventional preprocessing techniques, such as Mel Spectrogram, Perceptual Linear Prediction (PLP), and Learnable Spectrogram, achieve high classification accuracy but require large feature sets and significant computation. The low-latency and power efficiency benefits of neuromorphic computing offer a strong potential for audio classification. Here, we introduce memristive nanowire networks as a neuromorphic hardware preprocessing layer for spoken-digit classification, a capability not previously demonstrated. Nanowire networks extract compact, informative features directly from raw audio, achieving a favorable trade-off between accuracy, dimensionality reduction from the original audio size (data compression) , and training time efficiency. Compared with state-of-the-art software techniques, nanowire features reach 98.95% accuracy with 66 times data compression (XGBoost) and 97.9% accuracy with 255 times compression (Random Forest) in sub-second training latency. Across multiple classifiers nanowire features consistently achieve more than 90% accuracy with more than 62.5 times compression, outperforming features extracted by conventional state-of-the-art techniques such as MFCC in efficiency without loss of performance. Moreover, nanowire features achieve 96.5% accuracy classifying multispeaker audios, outperforming all state-of-the-art feature accuracies while achieving the highest data compression and lowest training time. Nanowire network preprocessing also enhances linear separability of audio data, improving simple classifier performance and generalizing across speakers. These results demonstrate that memristive nanowire networks provide a novel, low-latency, and data-efficient feature extraction approach, enabling high-performance neuromorphic audio classification.

翻译：高效音频特征提取对于低延迟、资源受限的语音识别至关重要。传统的预处理技术，如梅尔频谱图、感知线性预测（PLP）和可学习频谱图，虽然实现了高分类精度，但需要大规模特征集和大量计算。神经形态计算在低延迟和能效方面的优势为音频分类提供了巨大潜力。本文首次提出将忆阻纳米线网络作为神经形态硬件预处理层用于口语数字分类。纳米线网络直接从原始音频中提取紧凑且信息丰富的特征，在分类精度、原始音频尺寸的降维（数据压缩）以及训练时间效率之间实现了良好平衡。与最先进的软件技术相比，纳米线特征在亚秒级训练延迟下，通过XGBoost分类器实现了98.95%的准确率和66倍数据压缩，通过随机森林分类器实现了97.9%的准确率和255倍压缩。在多种分类器中，纳米线特征始终以超过62.5倍的压缩率实现90%以上的准确率，在效率上超越了MFCC等传统先进技术提取的特征，且性能无损。此外，纳米线特征在多说话者音频分类中达到96.5%的准确率，在实现最高数据压缩和最短训练时间的同时，超越了所有先进特征的准确率。纳米线网络预处理还增强了音频数据的线性可分性，提升了简单分类器的性能并实现了跨说话者的泛化。这些结果表明，忆阻纳米线网络提供了一种新颖、低延迟且数据高效的特征提取方法，为实现高性能神经形态音频分类奠定了基础。