Metamaterials you can talk to: Speech recognition with elastic neural networks

Abstract

To detect spoken commands, smart devices (for example, a speaker with Alexa or Siri) continuously convert acoustic waves to electronic signals, translate them into the digital domain, and analyze them in a signal processor. Each of these steps constantly consumes energy, imposing the need for tethered operation or large batteries. We propose to solve this problem using elastic neural networks, metamaterials consisting of arrays of coupled (potentially nonlinear) resonators. The frequencies and couplings of the resonators are optimized to maximise the speech classification accuracy (energy transmitted when excited with one word but not another). Even in purely linear metastructures, we observe binary classification accuracies exceeding 90% for a large number of pairs of words. This is demonstrated on a dataset from a large and diverse group of speakers. To attain these results, we have developed refined modelling techniques involving localised oscillations and machine learning. A unique feature of metamaterial-based speech processing is that speech classification is entirely passive, requiring no external energy. This is possible due to the very low energy dissipation of elastic waves.

In-sensor human gait analysis with machine learning in a wearable microfabricated accelerometer

“…Ultimately, the mechanical computing device in a sensor could be driven directly by a measured mechanical stimulus to produce without transduction and, in the most efficient manner, a processed output, such as a detection, classification, or control signal. Examples that have been discussed in the literature include resonating structures that are sensitive to sound and can identify certainly spoken commands 5 , metamaterial structures that can identify specific shapes from the positions of a set of contact points 6 , as well as various proposals for in materio computing 7 . The defining characteristic of these devices is that they can perform complex data processing, including the prediction or the classification of time-varying signals, with minimal or no electronic components that, when they are required, do not contribute substantially to the computing functions of the system.…”