Emotions Beyond Words: Non-Speech Audio Emotion Recognition With Edge Computing

TL;DR

This paper introduces a novel, resource-efficient non-speech emotion recognition system leveraging edge computing and knowledge distillation, enabling real-time emotion detection on limited devices with promising accuracy.

Contribution

It presents the first edge-computing framework for non-speech emotion recognition, utilizing knowledge distillation to maintain performance on resource-constrained devices.

Findings

Effective emotion detection from non-speech audio like crying and screaming.

Comparable performance to traditional models like MobileNet.

Demonstrates feasibility of deploying emotion recognition on edge devices.

Abstract

Non-speech emotion recognition has a wide range of applications including healthcare, crime control and rescue, and entertainment, to name a few. Providing these applications using edge computing has great potential, however, recent studies are focused on speech-emotion recognition using complex architectures. In this paper, a non-speech-based emotion recognition system is proposed, which can rely on edge computing to analyse emotions conveyed through non-speech expressions like screaming and crying. In particular, we explore knowledge distillation to design a computationally efficient system that can be deployed on edge devices with limited resources without degrading the performance significantly. We comprehensively evaluate our proposed framework using two publicly available datasets and highlight its effectiveness by comparing the results with the well-known MobileNet model. Our results demonstrate the feasibility and effectiveness of using edge computing for non-speech emotion detection, which can potentially improve applications that rely on emotion detection in communication networks. To the best of our knowledge, this is the first work on an edge-computing-based framework for detecting emotions in non-speech audio, offering promising directions for future research.