Audiovisual Discrimination between Laughter and Speech

Stavros Petridis; Maja Pantic

doi:10.1109/ICASSP.2008.4518810

Audiovisual Discrimination between Laughter and Speech

Stavros Petridis, Maja Pantic

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

48 Citations (Scopus)

147 Downloads (Pure)

Abstract

Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we show that integrating the information from audio and video leads to an improved reliability of audiovisual approach in comparison to single-modal approaches. We also investigated the level at which audiovisual information should be fused for the best performance. When tested on 96 audiovisual sequences depicting spontaneously displayed (as opposed to posed) laughter and speech episodes, the proposed audiovisual feature-level approach achieved a 86.9% recall rate with 76.7% precision.

Original language	Undefined
Title of host publication	ICASSP 2008 International Conference on Acoustics, Speech and Signal Processing
Place of Publication	Los Alamitos
Publisher	IEEE
Pages	5117-5120
Number of pages	4
ISBN (Print)	978-1-4244-1483-3
DOIs	https://doi.org/10.1109/ICASSP.2008.4518810
Publication status	Published - Apr 2008
Event	IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2008 - Caesars Palace, Las Vegas, United States Duration: 30 Mar 2008 → 4 Apr 2008

Publication series

Name
Publisher	IEEE Computer Society Press
Number	2008/16200
ISSN (Print)	1520-6149

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2008
Abbreviated title	ICASSP
Country/Territory	United States
City	Las Vegas
Period	30/03/08 → 4/04/08

Keywords

HMI-MI: MULTIMODAL INTERACTIONS
EC Grant Agreement nr.: FP7/211486
EWI-14794
Audiovisual data processing
METIS-255075
Nonlinguistic Information Processing
laughter detection
EC Grant Agreement nr.: FP6/0027787
IR-65263
Data Fusion

Access to Document

10.1109/ICASSP.2008.4518810

Cite this

@inproceedings{fd6e0007e03a461485b85ea967035b8b,

title = "Audiovisual Discrimination between Laughter and Speech",

abstract = "Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we show that integrating the information from audio and video leads to an improved reliability of audiovisual approach in comparison to single-modal approaches. We also investigated the level at which audiovisual information should be fused for the best performance. When tested on 96 audiovisual sequences depicting spontaneously displayed (as opposed to posed) laughter and speech episodes, the proposed audiovisual feature-level approach achieved a 86.9% recall rate with 76.7% precision.",

keywords = "HMI-MI: MULTIMODAL INTERACTIONS, EC Grant Agreement nr.: FP7/211486, EWI-14794, Audiovisual data processing, METIS-255075, Nonlinguistic Information Processing, laughter detection, EC Grant Agreement nr.: FP6/0027787, IR-65263, Data Fusion",

author = "Stavros Petridis and Maja Pantic",

note = "10.1109/ICASSP.2008.4518810 ; null ; Conference date: 30-03-2008 Through 04-04-2008",

year = "2008",

month = apr,

doi = "10.1109/ICASSP.2008.4518810",

language = "Undefined",

isbn = "978-1-4244-1483-3",

publisher = "IEEE",

number = "2008/16200",

pages = "5117--5120",

booktitle = "ICASSP 2008 International Conference on Acoustics, Speech and Signal Processing",

}

Petridis, S & Pantic, M 2008, Audiovisual Discrimination between Laughter and Speech. in ICASSP 2008 International Conference on Acoustics, Speech and Signal Processing., 10.1109/ICASSP.2008.4518810, IEEE, Los Alamitos, pp. 5117-5120, IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2008, Las Vegas, Nevada, United States, 30/03/08. https://doi.org/10.1109/ICASSP.2008.4518810

TY - GEN

T1 - Audiovisual Discrimination between Laughter and Speech

AU - Petridis, Stavros

AU - Pantic, Maja

N1 - 10.1109/ICASSP.2008.4518810

PY - 2008/4

Y1 - 2008/4

N2 - Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we show that integrating the information from audio and video leads to an improved reliability of audiovisual approach in comparison to single-modal approaches. We also investigated the level at which audiovisual information should be fused for the best performance. When tested on 96 audiovisual sequences depicting spontaneously displayed (as opposed to posed) laughter and speech episodes, the proposed audiovisual feature-level approach achieved a 86.9% recall rate with 76.7% precision.

AB - Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we show that integrating the information from audio and video leads to an improved reliability of audiovisual approach in comparison to single-modal approaches. We also investigated the level at which audiovisual information should be fused for the best performance. When tested on 96 audiovisual sequences depicting spontaneously displayed (as opposed to posed) laughter and speech episodes, the proposed audiovisual feature-level approach achieved a 86.9% recall rate with 76.7% precision.

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - EC Grant Agreement nr.: FP7/211486

KW - EWI-14794

KW - Audiovisual data processing

KW - METIS-255075

KW - Nonlinguistic Information Processing

KW - laughter detection

KW - EC Grant Agreement nr.: FP6/0027787

KW - IR-65263

KW - Data Fusion

U2 - 10.1109/ICASSP.2008.4518810

DO - 10.1109/ICASSP.2008.4518810

M3 - Conference contribution

SN - 978-1-4244-1483-3

SP - 5117

EP - 5120

BT - ICASSP 2008 International Conference on Acoustics, Speech and Signal Processing

PB - IEEE

CY - Los Alamitos

Y2 - 30 March 2008 through 4 April 2008

ER -