DMCA
Laughter detection in meetings (2004)
Cached
Download Links
| Venue: | in Proc. NIST Meeting Recognition Workshop |
| Citations: | 40 - 1 self |
BibTeX
@INPROCEEDINGS{Kennedy04laughterdetection,
author = {Lyndon S. Kennedy and Daniel P. W. Ellis},
title = {Laughter detection in meetings},
booktitle = {in Proc. NIST Meeting Recognition Workshop},
year = {2004}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We build a system to automatically detect laughter events in meetings, where laughter events are defined as points in the meeting where a number of the participants (more than just one) are laughing simultaneously. We implement our system using a support vector machine classifier trained on mel-frequency cepstral coefficients (MFCCs), delta MFCCs, modulation spectrum, and spatial cues from the time delay between two desktop microphones. We run our experiments on the ‘Bmr ’ subset of the ICSI Meeting Recorder corpus using just two table-top microphones and obtain detection results with a correct accept rate of 87 % and a false alarm rate of 13%. 1.
Keyphrases
laughter detection laughter event detection result table-top microphone time delay support vector machine classifier spatial cue delta mfccs icsi meeting recorder corpus false alarm rate desktop microphone correct accept rate modulation spectrum bmr subset mel-frequency cepstral coefficient
