Modeling Short-Term and Long-Term Dependencies of the Speech Signal for Paralinguistic Emotion Classification

Modeling Short-Term and Long-Term Dependencies of the Speech Signal for Paralinguistic Emotion Classification

Recently, Speech Emotion Recognition (SER) has become an important research topic of affective computing. It is a difficult problem, where some of the greatest challenges lie in the feature selection and representation tasks. A good feature representation should be able to reflect global trends as w...

Full description

Bibliographic Details
Main Authors: Oxana Vladimirovna Verkholyak, Heysem Kaya, Alexey Anatolievich Karpov
Format: Article
Language:English
Published: St.Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences 2019-02-01
Series:Труды СПИИРАН
Subjects:
Speech Emotion Recognition
Computational Paralinguistics
Affective Computing
Feature Representation
Context Modelling
Artificial Neural Networks
Long Short-Term Memory
Online Access:http://proceedings.spiiras.nw.ru/index.php/sp/article/view/3924

Internet

http://proceedings.spiiras.nw.ru/index.php/sp/article/view/3924

Similar Items