A Novel S-LDA Features for Automatic Emotion Recognition from Speech using 1-D CNN

Abstract

Emotions are explicit and serious mental activities, which find expression in speech, body gestures and facial features, etc. Speech is a fast, effective and the most convenient mode of human communication. Hence, speech has become the most researched modality in Automatic Emotion Recognition (AER). To extract the most discriminative and robust features from speech for Automatic Emotion Recognition (AER) recognition has yet remained a challenge. This paper, proposes a new algorithm named Shifted Linear Discriminant Analysis (S-LDA) to extract modified features from static low-level features like Mel-Frequency Cepstral Coefficients (MFCC) and Pitch. Further 1-D Convolution Neural Network (CNN) was applied to these modified features for extracting high-level features for AER. The performance evaluation of classification task for the proposed techniques has been carried out on the three standard databases: Berlin EMO-DB emotional speech database, Surrey Audio-Visual Expressed Emotion (SAVEE) database and eNTERFACE database. The proposed technique has shown to outperform the results obtained using state of the art techniques. The results shows that the best accuracy obtained for AER using the eNTERFACE database is 86.41%, on the Berlin database is 99.59% and with SAVEE database is 99.57%.

XEmoAccent: Embracing Diversity in Cross-Accent Emotion Recognition Using Deep Learning

“…Additionally, when compared to other classifiers, the MLP classifier achieves superior results across all three datasets. Shifted Linear Discriminant Analysis (S-LDA) is proposed in paper [34] to derive dynamic attributes from static lowlevel variables like MFCC and Pitch. These adjusted features go into a 1D-CNN to extract high-level features for automatic event recognition (AER).…”

“…Furthermore, the spectral centroid yields a single scalar value at (34), indicating where most of the audio signal's energy lies in frequency; spectral contrast with seven scaler values at index (35 -41) represents the difference in amplitude between peaks and troughs in the audio spectrum. Then, the third spectral roll-off feature at index (42) with a single value marks the frequency below which a specific percentage (e.g., 85%) of the total spectral energy lies.…”

Reliability Evaluation and Prediction Method with Small Samples

“…CNN has the ability of representation learning to pan unclassify the input information according to the hierarchical structure and it has been widely used in image classification (Bisht and Gupta, 2020), and speech recognition (Tiwari and Darji, 2022). 1D CNN, then, is an application of CNN model to the extraction of one-dimensional signals.…”