Home // SIGNAL 2016, The First International Conference on Advances in Signal, Image and Video Processing // View article

Analysis of Emotions in Vowels: a Recurrence Approach

Authors:
Angela Lombardi
Pietro Guccione

Keywords: Speech Emotion Recognition; Recurrence Plot; Recurrence Quantitative Analysis.

Abstract:
Emotional content in speech has been so far characterized by features based on linear source-filter models. However, the presence of nonlinear and chaotic phenomena in speech generation have been widely proven in literature. In this work, a novel framework has been developed to explore recurrence properties of vowels and describe nonlinear dynamics of speech. Experiments using a database of short spoken sentences emitted in the six basic emotions (anger, boredom, fear, happiness, neutral, sadness) show preliminary results of the approach.

Pages: 27 to 32

Copyright: Copyright (c) IARIA, 2016

Publication date: June 26, 2016

Published in: conference

ISSN: 2519-8432

ISBN: 978-1-61208-487-9

Location: Lisbon, Portugal

Dates: from June 26, 2016 to June 30, 2016