First Progresses in Evaluation of Resonance in Staff Selection through Speech Emotion Recognition

A schematic impression of the main parts of the system
A schematic impression of the main parts of the system

Authors:
Vitoantonio BevilacquaPietro GuccioneLuigi MascoloPasquale Pio PazienzaAngelo Antonio SalatinoMichele Pantaleo.

Abstract:

Speech Emotion Recognition (SER) is a hot research topic in the field of Human Computer Interaction. In this paper a SER system is developed with the aim of providing a classification of the “state of interest” of a human subject involved in a job interview. Classification of emotions is performed by analyzing the speech produced during the interview. The presented methods and results show just preliminary conclusions, as the work is part of a larger project including also analysis, investigation and classification of facial expressions and body gestures during human interaction. At the current state of the work, investigation is carried out by using software tools already available for free on the web; furthermore, the features extracted from the audio tracks are analyzed by studying their sensitivity to an audio compression stage. The Berlin Database of Emotional Speech (EmoDB) is exploited to provide the preliminary results.

Link to the article: http://link.springer.com/chapter/10.1007/978-3-642-39482-9_76

 

More information about the article/book: Intelligent Computing Theories and TechnologyLecture Notes in Computer Science Volume 7996, 2013, pp 658-671

Export Citation:

@incollection{
year={2013},
isbn={978-3-642-39481-2},
booktitle={Intelligent Computing Theories and Technology},
volume={7996},
series={Lecture Notes in Computer Science},
editor={Huang, De-Shuang and Jo, Kang-Hyun and Zhou, Yong-Quan and Han, Kyungsook},
doi={10.1007/978-3-642-39482-9_76},
title={First Progresses in Evaluation of Resonance in Staff Selection through Speech Emotion Recognition},
url={http://dx.doi.org/10.1007/978-3-642-39482-9_76},
publisher={Springer Berlin Heidelberg},
keywords={Emotional Speech Classification; Emotion Recognition; Acoustic Features Extraction},
author={Bevilacqua, Vitoantonio and Guccione, Pietro and Mascolo, Luigi and Pazienza, PasqualePio and Salatino, AngeloAntonio and Pantaleo, Michele},
pages={658-671},
language={English}
}