Integrating Information from Speech and Physiological Signals to Achieve Emotional Sensitivity

Jonghwa Kim; Elisabeth André; Matthias Rehm; Thurid Vogt; Johannes Wagner

Integrating Information from Speech and Physiological Signals to Achieve Emotional Sensitivity

Jonghwa Kim, Elisabeth André, Matthias Rehm, Thurid Vogt, Johannes Wagner

Human Machine Interaction

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

44 Citationer (Scopus)

Abstract

Recently, there has been a significant amount of work on the recognition of emotions from speech and biosignals. Most approaches to emotion recognition so far concentrate on a single modality and do not take advantage of the fact that an integrated multimodal analysis may help to resolve ambiguities and compensate
for errors. In this paper, we describe various methods for fusing physiological and voice data at the feature-level and the decision-level as well as a hybrid integration scheme. The results of the integrated recognition approach are then compared with the individual recognition results from each modality.

Originalsprog	Engelsk
Titel	Proceedings of the 9th European Conference on Speech Communication and Technology
Antal sider	4
Publikationsdato	2005
Sider	809-812
Status	Udgivet - 2005

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

HUMAINE: HUman MAchine Interaction Network on Emotions
Rehm, M.
01/03/2004 → 29/02/2008
Projekter: Projekt › Forskning

Citationsformater

@inproceedings{e9036e39804549eeae59808667c6eab6,

title = "Integrating Information from Speech and Physiological Signals to Achieve Emotional Sensitivity",

abstract = "Recently, there has been a significant amount of work on the recognition of emotions from speech and biosignals. Most approaches to emotion recognition so far concentrate on a single modality and do not take advantage of the fact that an integrated multimodal analysis may help to resolve ambiguities and compensatefor errors. In this paper, we describe various methods for fusing physiological and voice data at the feature-level and the decision-level as well as a hybrid integration scheme. The results of the integrated recognition approach are then compared with the individual recognition results from each modality.",

keywords = "Affective Computing, Speech Recognition, Emotion recognition",

author = "Jonghwa Kim and Elisabeth Andr{\'e} and Matthias Rehm and Thurid Vogt and Johannes Wagner",

year = "2005",

language = "English",

pages = "809--812",

booktitle = "Proceedings of the 9th European Conference on Speech Communication and Technology",

}

Integrating Information from Speech and Physiological Signals to Achieve Emotional Sensitivity. / Kim, Jonghwa; André, Elisabeth; Rehm, Matthias et al.
Proceedings of the 9th European Conference on Speech Communication and Technology. 2005. s. 809-812.

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Integrating Information from Speech and Physiological Signals to Achieve Emotional Sensitivity

AU - Kim, Jonghwa

AU - André, Elisabeth

AU - Rehm, Matthias

AU - Vogt, Thurid

AU - Wagner, Johannes

PY - 2005

Y1 - 2005

N2 - Recently, there has been a significant amount of work on the recognition of emotions from speech and biosignals. Most approaches to emotion recognition so far concentrate on a single modality and do not take advantage of the fact that an integrated multimodal analysis may help to resolve ambiguities and compensatefor errors. In this paper, we describe various methods for fusing physiological and voice data at the feature-level and the decision-level as well as a hybrid integration scheme. The results of the integrated recognition approach are then compared with the individual recognition results from each modality.

AB - Recently, there has been a significant amount of work on the recognition of emotions from speech and biosignals. Most approaches to emotion recognition so far concentrate on a single modality and do not take advantage of the fact that an integrated multimodal analysis may help to resolve ambiguities and compensatefor errors. In this paper, we describe various methods for fusing physiological and voice data at the feature-level and the decision-level as well as a hybrid integration scheme. The results of the integrated recognition approach are then compared with the individual recognition results from each modality.

KW - Affective Computing

KW - Speech Recognition

KW - Emotion recognition

M3 - Article in proceeding

SP - 809

EP - 812

BT - Proceedings of the 9th European Conference on Speech Communication and Technology

ER -

Integrating Information from Speech and Physiological Signals to Achieve Emotional Sensitivity

Abstract

AUB Link

Fingeraftryk

Projekter

HUMAINE: HUman MAchine Interaction Network on Emotions

Citationsformater