Exploring Language-Independent Emotional Acoustic Features via Feature Selection
Machine Learning
2010-09-02 v1
Abstract
We propose a novel feature selection strategy to discover language-independent acoustic features that tend to be responsible for emotions regardless of languages, linguistics and other factors. Experimental results suggest that the language-independent feature subset discovered yields the performance comparable to the full feature set on various emotional speech corpora.
Cite
@article{arxiv.1009.0117,
title = {Exploring Language-Independent Emotional Acoustic Features via Feature Selection},
author = {Arslan Shaukat and Ke Chen},
journal= {arXiv preprint arXiv:1009.0117},
year = {2010}
}
Comments
15 pages, 2 figures, 6 tables