2025/08/06 by Paul, Durjoy Chandra, Gaurob Saha, Saha, Gaurob +2
Psychology · Computer Science · #Emotion and Mood Recognition #Speech Recognition and Synthesis
paper · pdf · doi:10.48550/arxiv.2508.06321
Recognizing emotional signals in speech has a significant impact on enhancing the effectiveness of human-computer interaction (HCI). This study introduces EmoAugNet, a hybrid deep learning framework, that incorporates Long Short-Term Memory (LSTM) layers with one-dimensional Convolutional Neural Networks (1D-CNN) to enable reliable Speech Emotion Recognition (SER). The quality and variety of the features that are taken from speech signals have a significant impact on how well SER systems perform. A comprehensive speech data augmentation strategy was used to combine both traditional methods, such as noise addition, pitch shifting, and time stretching, with a novel combination-based augmentation pipeline to enhance generalization and reduce overfitting. Each audio sample was transformed into a high-dimensional feature vector using root mean square energy (RMSE), Mel-frequency Cepstral Coefficient (MFCC), and zero-crossing rate (ZCR). Our model with ReLU activation has a weighted accuracy of 95.78% and unweighted accuracy of 92.52% on the IEMOCAP dataset and, with ELU activation, has a weighted accuracy of 96.75% and unweighted accuracy of 91.28%. On the RAVDESS dataset, we get a weighted accuracy of 94.53% and 94.98% unweighted accuracy for ReLU activation and 93.72% weighted accuracy and 94.64% unweighted accuracy for ELU activation. These results highlight EmoAugNet's effectiveness in improving the robustness and performance of SER systems through integated data augmentation and hybrid modeling.