In this paper, we address the question whether prosodically/ linguistically prominent syllables carrying the word accent (stressed syllables) are better indicators for emotional marking than unstressed syllables. To this aim, we use a large spontaneous database with children interacting with Sony's Aibo robot, annotated with word-based emotion labels, large acoustic-prosodic feature vectors, and support vector machines as classifiers. It turns out that, in most of the cases, stressed syllables are better emotion markers than unstressed syllables. Moreover, we discuss specific phenomena such as vocatives and other constellations, to be modelled in future studies.
Index Terms: emotion, linguistics, paralinguistics, word accent, lexical stress, automatic classification
Cite as: Seppi, D., Batliner, A., Steidl, S., Schuller, B., Nöth, E. (2010) Word accent and emotion. Proc. Speech Prosody 2010, paper 053
@inproceedings{seppi10_speechprosody,
author={Dino Seppi and Anton Batliner and Stefan Steidl and Björn Schuller and Elmar Nöth},
title={{Word accent and emotion}},
year=2010,
booktitle={Proc. Speech Prosody 2010},
pages={paper 053}
}