Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-organized Operational Layer
This work is significant for developers of robotic applications and embedded devices, as it offers a more efficient and lightweight approach to speech command recognition, addressing the memory and energy constraints of such environments.
This paper addresses the challenge of speech command recognition in computationally constrained environments by proposing a novel network layer. This layer enhances the feature representation using Taylor expansion and quadratic forms, leading to improved recognition accuracy on both Google Speech Commands and Synthetic Speech Commands datasets.
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.