Acoustic Feature Analysis in Speech Emotion Primitives Estimation (bibtex)
	address = {Makuhari, Japan},
	title = {Acoustic {Feature} {Analysis} in {Speech} {Emotion} {Primitives} {Estimation}},
	url = {},
	abstract = {We recently proposed a family of robust linear and nonlin- ear estimation techniques for recognizing the three emotion primitives–valence, activation, and dominance–from speech. These were based on both local and global speech duration, en- ergy, MFCC and pitch features. This paper aims to study the relative importance of these four categories of acoustic features in this emotion estimation context. Three measures are consid- ered: the number of features from each category when all fea- tures are used in selection, the mean absolute error (MAE) when each category is used separately, and the MAE when a category is excluded from feature selection. We find that the relative importance is in the order of MFCC {\textbackslash}textbackslashtextgreater Energy ≈ Pitch {\textbackslash}textbackslashtextgreater Du- ration. Additionally, estimator fusion almost always improves performance, and locally weighted fusion always outperforms average fusion regardless of the number of features used.},
	booktitle = {Proceedings of {InterSpeech}},
	author = {Wu, Dongrui and Parsons, Thomas D. and Narayanan, Shrikanth},
	month = sep,
	year = {2010},
	keywords = {MedVR}
Powered by bibtexbrowser