Unsupervised low-rank representations for speech emotion recognition

TL;DR

This paper explores the use of linear and non-linear dimensionality reduction techniques to create low-rank feature representations that improve speech emotion recognition accuracy across different datasets and classifiers.

Contribution

It demonstrates that unsupervised dimensionality reduction enhances speech emotion recognition performance and provides visual insights into feature discriminability.

Findings

Low-dimensional features improve SER accuracy

Dimensionality reduction helps mitigate curse of dimensionality

Visualizations reveal discriminative feature structures

Abstract

We examine the use of linear and non-linear dimensionality reduction algorithms for extracting low-rank feature representations for speech emotion recognition. Two feature sets are used, one based on low-level descriptors and their aggregations (IS10) and one modeling recurrence dynamics of speech (RQA), as well as their fusion. We report speech emotion recognition (SER) results for learned representations on two databases using different classification methods. Classification with low-dimensional representations yields performance improvement in a variety of settings. This indicates that dimensionality reduction is an effective way to combat the curse of dimensionality for SER. Visualization of features in two dimensions provides insight into discriminatory abilities of reduced feature sets.