论文标题
使用神经体系结构搜索和量化的资源有效的DNN用于关键字发现关键字
Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization
论文作者
论文摘要
本文介绍了神经体系结构搜索（NAS），以自动发现在有限的资源环境中用于关键字发现（KWS）的小型模型。我们采用可区分的NAS方法来优化卷积神经网络（CNN）的结构，以最大程度地提高分类精度，同时最大程度地减少每个推理的操作数量。仅使用NAS，我们能够在Google语音命令数据集中获得具有95.4％精度的高效模型，其中具有494.8 KB的内存使用和1960万个操作。此外，使用权重量化用于进一步减少记忆消耗。我们表明，可以使用重量量化到低宽度（例如1位）而不会实质性损失。通过将输入功能的数量从10 MFCC增加到20 MFCC，我们能够在340.1 kb的内存使用情况下将准确性提高到96.3％，而2710万次操作。
This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) to maximize the classification accuracy while minimizing the number of operations per inference. Using NAS only, we were able to obtain a highly efficient model with 95.4% accuracy on the Google speech commands dataset with 494.8 kB of memory usage and 19.6 million operations. Additionally, weight quantization is used to reduce the memory consumption even further. We show that weight quantization to low bit-widths (e.g. 1 bit) can be used without substantial loss in accuracy. By increasing the number of input features from 10 MFCC to 20 MFCC we were able to increase the accuracy to 96.3% at 340.1 kB of memory usage and 27.1 million operations.
