Imagen de Portada

Speech Emotion Recognition on MELD and RAVDESS Datasets Using CNN

Guardado en:
Publicado en:Information vol. 16, no. 7 (2025), p. 518-536
Autor principal: Waleed, Gheed T
Otros Autores: Shaker, Shaimaa H
Publicado:
MDPI AG
Materias:
Data augmentation
Accuracy
Embedded systems
Deep learning
Datasets
Wavelet transforms
Affective computing
Artificial intelligence
Human-computer interface
Emotion recognition
Spectrograms
Artificial neural networks
Neural networks
Ablation
Support vector machines
Random noise
Emotions
Methods
Acoustics
Real time
Speech
Speech recognition
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen: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.
ISSN:2078-2489
DOI:10.3390/info16070518
Fuente:Advanced Technologies & Aerospace Database