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.
Cite as: Paraskevopoulos, G., Tzinis, E., Ellinas, N., Giannakopoulos, T., Potamianos, A. (2019) Unsupervised Low-Rank Representations for Speech Emotion Recognition. Proc. Interspeech 2019, 939-943, doi: 10.21437/Interspeech.2019-2769
@inproceedings{paraskevopoulos19_interspeech,
author={Georgios Paraskevopoulos and Efthymios Tzinis and Nikolaos Ellinas and Theodoros Giannakopoulos and Alexandros Potamianos},
title={{Unsupervised Low-Rank Representations for Speech Emotion Recognition}},
year=2019,
booktitle={Proc. Interspeech 2019},
pages={939--943},
doi={10.21437/Interspeech.2019-2769}
}