# Unsupervised low-rank representations for speech emotion recognition

arXiv: https://arxiv.org/abs/2104.07072 · HTML: https://mlsanity.com/paper/2104.07072/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 37 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 2 of 2)

- [Integrating Recurrence Dynamics for Speech Emotion Recognition](https://mlsanity.com/paper/1811.04133/) (2018)
- [Pattern Search Multidimensional Scaling](https://mlsanity.com/paper/1806.00416/) (2018)

## Built on by (most cited first, 3 of 3)

- [Active Learning Based Fine-Tuning Framework for Speech Emotion Recognition](https://mlsanity.com/paper/2310.00283/) (2023)
- [Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition](https://mlsanity.com/paper/2405.00307/) (2024)
- [Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Research](https://mlsanity.com/paper/2604.25776/) (2026)

## Abstract (arXiv)

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.