Multiresolution analysis (discrete wavelet transform) through Daubechies family for emotion recognition in speech

TL;DR

This paper demonstrates that wavelet-based feature extraction using Daubechies wavelets effectively classifies seven human emotional states from speech signals with high accuracy, even under challenging channel conditions.

Contribution

It introduces a wavelet-based feature extraction method for emotion recognition in speech that outperforms traditional features and works well with neural network classifiers.

Findings

High accuracy in classifying seven emotional states.

Wavelet features suffice without classical frequency-time features.

Effective under non-ideal channel conditions.

Abstract

We propose a study of the mathematical properties of voice as an audio signal. This work includes signals in which the channel conditions are not ideal for emotion recognition. Multiresolution analysis discrete wavelet transform was performed through the use of Daubechies Wavelet Family (Db1-Haar, Db 6, Db8, Db10) allowing the decomposition of the initial audio signal into sets of coefficients on which a set of features was extracted and analyzed statistically in order to differentiate emotional states. ANNs proved to be a system that allows an appropriate classification of such states. This study shows that the extracted features using wavelet decomposition are enough to analyze and extract emotional content in audio signals presenting a high accuracy rate in classification of emotional states without the need to use other kinds of classical frequency-time features. Accordingly, this paper seeks to characterize mathematically the six basic emotions in humans: boredom, disgust, happiness, anxiety, anger and sadness, also included the neutrality, for a total of seven states to identify.