Decision-Level Fusion for Audio-Visual Laughter Detection

  • 16 Citations

Abstract

Laughter is a highly variable signal, which can be caused by a spectrum of emotions. This makes the automatic detection of laugh- ter a challenging, but interesting task. We perform automatic laughter detection using audio-visual data from the AMI Meeting Corpus. Audio- visual laughter detection is performed by fusing the results of separate audio and video classifiers on the decision level. This results in laughter detection with a significantly higher AUC-ROC than single-modality classification.
Original languageUndefined
Title of host publication5th International Workshop, MLMI 2008
EditorsAndrei Popescu-Belis, Rainer Stiefelhagen
Place of PublicationBerlin
PublisherSpringer Verlag
Pages137-148
Number of pages12
ISBN (Print)978-3-540-85852-2
DOIs
StatePublished - Sep 2008

Publication series

NameLecture Notes on Computer Science
PublisherSpringer Verlag
Volume5237/2008
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Fingerprint

humor
video
classification
conference

Keywords

  • EWI-13404
  • IR-62452
  • METIS-256121
  • HMI-CI: Computational Intelligence

Cite this

Reuderink, B., Poel, M., Truong, K. P., Poppe, R. W., & Pantic, M. (2008). Decision-Level Fusion for Audio-Visual Laughter Detection. In A. Popescu-Belis, & R. Stiefelhagen (Eds.), 5th International Workshop, MLMI 2008 (pp. 137-148). [10.1007/978-3-540-85853-9_13] (Lecture Notes on Computer Science; Vol. 5237/2008). Berlin: Springer Verlag. DOI: 10.1007/978-3-540-85853-9_13

Reuderink, B.; Poel, Mannes; Truong, Khiet Phuong; Poppe, Ronald Walter; Pantic, Maja / Decision-Level Fusion for Audio-Visual Laughter Detection.

5th International Workshop, MLMI 2008. ed. / Andrei Popescu-Belis; Rainer Stiefelhagen. Berlin : Springer Verlag, 2008. p. 137-148 10.1007/978-3-540-85853-9_13 (Lecture Notes on Computer Science; Vol. 5237/2008).

Research output: Scientific - peer-reviewConference contribution

@inbook{3ccbecda68174b22a75deb125c931dda,
title = "Decision-Level Fusion for Audio-Visual Laughter Detection",
abstract = "Laughter is a highly variable signal, which can be caused by a spectrum of emotions. This makes the automatic detection of laugh- ter a challenging, but interesting task. We perform automatic laughter detection using audio-visual data from the AMI Meeting Corpus. Audio- visual laughter detection is performed by fusing the results of separate audio and video classifiers on the decision level. This results in laughter detection with a significantly higher AUC-ROC than single-modality classification.",
keywords = "EWI-13404, IR-62452, METIS-256121, HMI-CI: Computational Intelligence",
author = "B. Reuderink and Mannes Poel and Truong, {Khiet Phuong} and Poppe, {Ronald Walter} and Maja Pantic",
year = "2008",
month = "9",
doi = "10.1007/978-3-540-85853-9_13",
isbn = "978-3-540-85852-2",
series = "Lecture Notes on Computer Science",
publisher = "Springer Verlag",
pages = "137--148",
editor = "Andrei Popescu-Belis and Rainer Stiefelhagen",
booktitle = "5th International Workshop, MLMI 2008",

}

Reuderink, B, Poel, M, Truong, KP, Poppe, RW & Pantic, M 2008, Decision-Level Fusion for Audio-Visual Laughter Detection. in A Popescu-Belis & R Stiefelhagen (eds), 5th International Workshop, MLMI 2008., 10.1007/978-3-540-85853-9_13, Lecture Notes on Computer Science, vol. 5237/2008, Springer Verlag, Berlin, pp. 137-148. DOI: 10.1007/978-3-540-85853-9_13

Decision-Level Fusion for Audio-Visual Laughter Detection. / Reuderink, B.; Poel, Mannes; Truong, Khiet Phuong; Poppe, Ronald Walter; Pantic, Maja.

5th International Workshop, MLMI 2008. ed. / Andrei Popescu-Belis; Rainer Stiefelhagen. Berlin : Springer Verlag, 2008. p. 137-148 10.1007/978-3-540-85853-9_13 (Lecture Notes on Computer Science; Vol. 5237/2008).

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - Decision-Level Fusion for Audio-Visual Laughter Detection

AU - Reuderink,B.

AU - Poel,Mannes

AU - Truong,Khiet Phuong

AU - Poppe,Ronald Walter

AU - Pantic,Maja

PY - 2008/9

Y1 - 2008/9

N2 - Laughter is a highly variable signal, which can be caused by a spectrum of emotions. This makes the automatic detection of laugh- ter a challenging, but interesting task. We perform automatic laughter detection using audio-visual data from the AMI Meeting Corpus. Audio- visual laughter detection is performed by fusing the results of separate audio and video classifiers on the decision level. This results in laughter detection with a significantly higher AUC-ROC than single-modality classification.

AB - Laughter is a highly variable signal, which can be caused by a spectrum of emotions. This makes the automatic detection of laugh- ter a challenging, but interesting task. We perform automatic laughter detection using audio-visual data from the AMI Meeting Corpus. Audio- visual laughter detection is performed by fusing the results of separate audio and video classifiers on the decision level. This results in laughter detection with a significantly higher AUC-ROC than single-modality classification.

KW - EWI-13404

KW - IR-62452

KW - METIS-256121

KW - HMI-CI: Computational Intelligence

U2 - 10.1007/978-3-540-85853-9_13

DO - 10.1007/978-3-540-85853-9_13

M3 - Conference contribution

SN - 978-3-540-85852-2

T3 - Lecture Notes on Computer Science

SP - 137

EP - 148

BT - 5th International Workshop, MLMI 2008

PB - Springer Verlag

ER -

Reuderink B, Poel M, Truong KP, Poppe RW, Pantic M. Decision-Level Fusion for Audio-Visual Laughter Detection. In Popescu-Belis A, Stiefelhagen R, editors, 5th International Workshop, MLMI 2008. Berlin: Springer Verlag. 2008. p. 137-148. 10.1007/978-3-540-85853-9_13. (Lecture Notes on Computer Science). Available from, DOI: 10.1007/978-3-540-85853-9_13