A Comprehensive Analysis of Data Augmentation Methods for Speech Emotion Recognition
Author:
Open Access
- 9 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 111647-111669
Abstract
The limited availability of labeled emotional speech data remains a significant challenge in developing robust speech emotion recognition systems. This paper presents a comprehensive investigation into the effectiveness of diverse data augmentation strategies for enhancing emotion recognition performance. Three different data augmentation categories are examined: audio-based transformations, image-based modifications, and feature-level synthesis. Seventeen transformations are used in audio-based data augmentation to change the raw audio signal’s time and frequency content. Eight transformations, such as shifting, rotating, and zooming, are applied to the spectrogram images for image-based data augmentation. The SpecAugment method is also used to transform the spectrograms into versions with masked time and frequency axes. In feature-space-based approaches, new feature vectors are generated using five oversampling algorithms and a generative adversarial network. Experimental results from EMO-DB and IEMOCAP datasets demonstrate that the data augmentation approaches enhance emotion classification performance by up to six percent. The empirical evidence indicates that training sets augmented through combinations of audio-based transformations yield the highest performance gains. In contrast, the GAN-based approach fails to produce improvements in classification performance.Keywords
This publication has 88 references indexed in Scilit:
- On a Time-Frequency Blurring Operator with Applications in Data AugmentationJournal of Fourier Analysis and Applications, 2025
- A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition2024
- SENet-based speech emotion recognition using synthesis-style transfer data augmentationInternational Journal of Speech Technology, 2023
- Generative Adversarial Nets2023
- Deep Convolutional Neural Network and Gray Wolf Optimization Algorithm for Speech Emotion RecognitionCircuits, Systems, and Signal Processing, 2022
- Convolutional neural network-based cross-corpus speech emotion recognition with data augmentation and features fusionMachine Vision and Applications, 2022
- Augmented Audio Data in Improving Speech Emotion Classification Tasks2021
- Vocal Cues Underlying Youth and Adult Portrayals of Socio-emotional ExpressionsJournal of Nonverbal Behavior, 2017
- Towards real-time speech emotion recognition for affective e-learningEducation and Information Technologies, 2015
- IEMOCAP: interactive emotional dyadic motion capture databaseLanguage Resources and Evaluation, 2008