Energy Efficient Graph-Based Hybrid Learning for Speech Emotion Recognition on Humanoid Robot

Haowen Wu; Hanyue Xu; Kah Phooi Seng; Jieli Chen; Li Minn Ang

doi:10.3390/electronics13061151

Back

Energy Efficient Graph-Based Hybrid Learning for Speech Emotion Recognition on Humanoid Robot

Journal article

Open access

Peer reviewed

Energy Efficient Graph-Based Hybrid Learning for Speech Emotion Recognition on Humanoid Robot

Haowen Wu, Hanyue Xu, Kah Phooi Seng, Jieli Chen and Li Minn Ang

Electronics, Vol.13(6), pp.1-19

2024

DOI: https://doi.org/10.3390/electronics13061151

Files and links (1)

pdf

electronics-13-011516.07 MBDownload View

Published VersionCC BY V4.0, Open Access

Abstract

energy efficient deep learning

graph convolutional neural network

speech emotion recognition

humanoid robot

This paper presents a novel deep graph-based learning technique for speech emotion recognition which has been specifically tailored for energy efficient deployment within humanoid robots. Our methodology represents a fusion of scalable graph representations, rooted in the foundational principles of graph signal processing theories. By delving into the utilization of cycle or line graphs as fundamental constituents shaping a robust Graph Convolution Network (GCN)-based architecture, we propose an approach which allows the capture of relationships between speech signals to decode intricate emotional patterns and responses. Our methodology is validated and benchmarked against established databases such as IEMOCAP and MSP-IMPROV. Our model outperforms standard GCNs and prevalent deep graph architectures, demonstrating performance levels that align with state-of-the-art methodologies. Notably, our model achieves this feat while significantly reducing the number of learnable parameters, thereby increasing computational efficiency and bolstering its suitability for resource-constrained environments. This proposed energy-efficient graph-based hybrid learning methodology is applied towards multimodal emotion recognition within humanoid robots. Its capacity to deliver competitive performance while streamlining computational complexity and energy efficiency represents a novel approach in evolving emotion recognition systems, catering to diverse real-world applications where precision in emotion recognition within humanoid robots stands as a pivotal requisite.

Details

Title: Energy Efficient Graph-Based Hybrid Learning for Speech Emotion Recognition on Humanoid Robot
Authors: Haowen Wu - Xi’an Jiaotong-Liverpool University
Hanyue Xu - Xi’an Jiaotong-Liverpool University
Kah Phooi Seng (Corresponding Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Jieli Chen - Xi’an Jiaotong-Liverpool University
Li Minn Ang - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Publication details: Electronics, Vol.13(6), pp.1-19
Publisher: MDPI AG
Date published: 2024
DOI: 10.3390/electronics13061151
ISSN: 2079-9292
Copyright note: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Data Availability: The research dataset is IEMOCAP. Link: https://paperswithcode.com/dataset/iemocap (accessed on 3 July 2023).
Organisation Unit: School of Science, Technology and Engineering
Language: English
Record Identifier: 991014498102621
Output Type: Journal article

Metrics

18 Record Views

3 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Computer Science, Information Systems; Engineering, Electrical & Electronic; Physics, Applied