Neural Architecture Search for Energy Efficient Always-on Audio Models
This work addresses the need for energy-efficient models for always-on audio tasks on mobile and edge devices, representing an incremental improvement through NAS modifications.
The paper tackled the problem of designing energy-efficient neural networks for always-on audio classification on mobile devices by introducing modifications to neural architecture search (NAS) that simultaneously optimize for accuracy, energy efficiency, and memory usage. The result was an order of magnitude reduction in energy per inference and a smaller memory footprint compared to baseline MobileNetV1/V2, with a slight improvement in task accuracy on a sound-event classification dataset.
Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches (NAS) that improve the chance of success in practical situations. Our search simultaneously optimizes for network accuracy, energy efficiency and memory usage. We benchmark the performance of our search on real hardware, but since running thousands of tests with real hardware is difficult we use a random forest model to roughly predict the energy usage of a candidate network. We present a search strategy that uses both Bayesian and regularized evolutionary search with particle swarms, and employs early-stopping to reduce the computational burden. Our search, evaluated on a sound-event classification dataset based upon AudioSet, results in an order of magnitude less energy per inference and a much smaller memory footprint than our baseline MobileNetV1/V2 implementations while slightly improving task accuracy. We also demonstrate how combining a 2D spectrogram with a convolution with many filters causes a computational bottleneck for audio classification and that alternative approaches reduce the computational burden but sacrifice task accuracy.