@inproceedings {pub2627pub2760,
	title = {Improving the Naturalness of the Human-Machine Interaction via Audio-visual Word Prominence Detection},
	author = {Martin Ernst Heckmann},
	year = {2014},
	month = {September},
	abstract = {In this paper we investigate how word prominence can be detected from the acoustic signal and movements of the speaker{\textquoteright}s head and mouth.
Our research is based on a corpus with 12 English speakers which contains in addition to the speech signal also videos of the talker{\textquoteright}s head. 
To extract the word prominence information we use on one hand functionals calculated on the features and on the other hand Functional PCA (FPCA) to extract information from the contours.
Combining the functionals and the contour information we obtain a discrimination accuracy between prominent and non-prominent words of 81\%.
We show in particular that the visual channel is very informative for some speakers.
Furthermore, we also introduce a system which extracts the prominence information online while a user is interacting with the system.
The online system only uses acoustic information.},
	publisher = {Springer, LNCS, LNAI, LNBI},
	booktitle = {2nd Workshop on Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction},
	city = {Singapore}
}