Speech Emotion Recognition on MELD and RAVDESS Datasets Using CNN
Information · 21.06.2025 · 16 (7) · 518
DOI: 10.3390/info16070518 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 21.06.2025. Verfasst von Gheed T. Waleed und 1 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Speech emotion recognition (SER) plays a vital role in enhancing human–computer interaction (HCI) and can be applied in affective computing, virtual support, and healthcare. This research presents a high-performance SER framework based on a lightweight 1D Convolutional Neural Network (1D-CNN) and a multi-feature fusion technique. Rather than employing spectrograms as image-based input, frame-level characteristics (Mel-Frequency Cepstral Coefficients, Mel-Spectrograms, and Chroma vectors) are calculated throughout the sequences to preserve temporal information and reduce the computing expense. The model attained classification accuracies of 94.0% on MELD (multi-party talks) and 91.9% on RAVDESS (acted speech). Ablation experiments demonstrate that the integration of complimentary features significantly outperforms the utilisation of a singular feature as a baseline. Data augmentation techniques, including Gaussian noise and time shifting, enhance model generalisation. The proposed method demonstrates significant potential for real-time emotion recognition using audio only in embedded or resource-constrained devices.
Zitieren
APA
Waleed, G. T., & Shaker, S. H. (2025). Speech Emotion Recognition on MELD and RAVDESS Datasets Using CNN. Information, 16(7), 518. https://doi.org/10.3390/info16070518
Vancouver
Waleed GT, Shaker SH. Speech Emotion Recognition on MELD and RAVDESS Datasets Using CNN. Information. 2025;16(7):518. doi:10.3390/info16070518
BibTeX
@article{Waleed2025,
author = {Waleed, Gheed T. and Shaker, Shaimaa H.},
title = {Speech Emotion Recognition on MELD and RAVDESS Datasets Using CNN},
journal = {Information},
year = {2025},
volume = {16},
number = {7},
pages = {518},
doi = {10.3390/info16070518}
}
EUVIMED