Is deception emotional? An emotion-driven predictive approach

Shahin Amiriparian; Jouni Pohjalainen; Erik Marchi; Sergey Pugachevskiy; Björn Schuller

doi:10.21437/Interspeech.2016-565

Is deception emotional? An emotion-driven predictive approach

Shahin Amiriparian, Jouni Pohjalainen, Erik Marchi, Sergey Pugachevskiy, Björn Schuller

Research output: Contribution to journal › Conference article › peer-review

21 Scopus citations

Abstract

In this paper, we propose a method for automatically detecting deceptive speech by relying on predicted scores derived from emotion dimensions such as arousal, valence, regulation, and emotion categories. The scores are derived from task-dependent models trained on the GEMEP emotional speech database. Inputs from the INTERSPEECH 2016 Computational Paralinguistics Deception sub-challenge are processed to obtain predictions of emotion attributes and associated scores that are then used as features in detecting deception. We show that using the new emotion-related features, it is possible to improve upon the challenge baseline.

Original language	English
Pages (from-to)	2011-2015
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	08-12-September-2016
DOIs	https://doi.org/10.21437/Interspeech.2016-565
State	Published - 2016
Externally published	Yes
Event	17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016 - San Francisco, United States Duration: 8 Sep 2016 → 16 Sep 2016

Keywords

Computational paralinguistics
Deception
Emotion

Access to Document

10.21437/Interspeech.2016-565

Cite this

@article{c9f7aa8f36b649ee85f7d404d0772146,

title = "Is deception emotional? An emotion-driven predictive approach",

abstract = "In this paper, we propose a method for automatically detecting deceptive speech by relying on predicted scores derived from emotion dimensions such as arousal, valence, regulation, and emotion categories. The scores are derived from task-dependent models trained on the GEMEP emotional speech database. Inputs from the INTERSPEECH 2016 Computational Paralinguistics Deception sub-challenge are processed to obtain predictions of emotion attributes and associated scores that are then used as features in detecting deception. We show that using the new emotion-related features, it is possible to improve upon the challenge baseline.",

keywords = "Computational paralinguistics, Deception, Emotion",

author = "Shahin Amiriparian and Jouni Pohjalainen and Erik Marchi and Sergey Pugachevskiy and Bj{\"o}rn Schuller",

note = "Publisher Copyright: Copyright {\textcopyright} 2016 ISCA.; 17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016 ; Conference date: 08-09-2016 Through 16-09-2016",

year = "2016",

doi = "10.21437/Interspeech.2016-565",

language = "English",

volume = "08-12-September-2016",

pages = "2011--2015",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

}

TY - JOUR

T1 - Is deception emotional? An emotion-driven predictive approach

AU - Amiriparian, Shahin

AU - Pohjalainen, Jouni

AU - Marchi, Erik

AU - Pugachevskiy, Sergey

AU - Schuller, Björn

PY - 2016

Y1 - 2016

N2 - In this paper, we propose a method for automatically detecting deceptive speech by relying on predicted scores derived from emotion dimensions such as arousal, valence, regulation, and emotion categories. The scores are derived from task-dependent models trained on the GEMEP emotional speech database. Inputs from the INTERSPEECH 2016 Computational Paralinguistics Deception sub-challenge are processed to obtain predictions of emotion attributes and associated scores that are then used as features in detecting deception. We show that using the new emotion-related features, it is possible to improve upon the challenge baseline.

AB - In this paper, we propose a method for automatically detecting deceptive speech by relying on predicted scores derived from emotion dimensions such as arousal, valence, regulation, and emotion categories. The scores are derived from task-dependent models trained on the GEMEP emotional speech database. Inputs from the INTERSPEECH 2016 Computational Paralinguistics Deception sub-challenge are processed to obtain predictions of emotion attributes and associated scores that are then used as features in detecting deception. We show that using the new emotion-related features, it is possible to improve upon the challenge baseline.

KW - Computational paralinguistics

KW - Deception

KW - Emotion

UR - http://www.scopus.com/inward/record.url?scp=84994338824&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2016-565

DO - 10.21437/Interspeech.2016-565

M3 - Conference article

AN - SCOPUS:84994338824

SN - 2308-457X

VL - 08-12-September-2016

SP - 2011

EP - 2015

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016

Y2 - 8 September 2016 through 16 September 2016

ER -

Is deception emotional? An emotion-driven predictive approach

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this