Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-organized Operational Layer

TL;DR

This paper introduces a quadratic self-organized operational layer to improve speech command recognition accuracy in lightweight models suitable for embedded devices, using Taylor expansion and quadratic forms.

Contribution

A novel quadratic layer enhances lightweight speech recognition models, improving accuracy without increasing computational complexity significantly.

Findings

Improved recognition accuracy on GSC and SSC datasets.

Effective enhancement of lightweight models for embedded speech recognition.

Demonstrated efficiency of quadratic layer in resource-constrained environments.

Abstract

Automatic classification of speech commands has revolutionized human computer interactions in robotic applications. However, employed recognition models usually follow the methodology of deep learning with complicated networks which are memory and energy hungry. So, there is a need to either squeeze these complicated models or use more efficient light-weight models in order to be able to implement the resulting classifiers on embedded devices. In this paper, we pick the second approach and propose a network layer to enhance the speech command recognition capability of a lightweight network and demonstrate the result via experiments. The employed method borrows the ideas of Taylor expansion and quadratic forms to construct a better representation of features in both input and hidden layers. This richer representation results in recognition accuracy improvement as shown by extensive experiments on Google speech commands (GSC) and synthetic speech commands (SSC) datasets.