Enhancements in Immediate Speech Emotion Detection: Harnessing Prosodic and Spectral Characteristics

Short summary

A new speech emotion recognition system uses Diffusion Map for dimensionality reduction and an ensemble of Decision Trees and KNN classifiers, achieving 79.52% accuracy with Multilayer Perceptron (MLP) and 70.86% with SVM, outperforming previous benchmarks.

AI-generated from the title and abstract; the full text is not read.