Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·

Automatic detection of laughter

Publication files not online:

Author: Truong, K.P. · Leeuwen, D.A. van
Institution: TNO Defensie en Veiligheid
Source:9th European Conference on Speech Communication and Technology, 4 September 2005 through 8 September 2005, Lisbon,, 485-488
Identifier: 15958
Keywords: Automatic speech recognition · Laughter · Automation · Error correction · Linearization · Linguistics · Mathematical models · Modulation · Speech analysis · White noise · Emotional state · Gaussian Mixture Models · Modulation spectra · Paralinguistic events · Gesture recognition


In the context of detecting ‘paralinguistic events’ with the aim to make classification of the speaker’s emotional state possible, a detector was developed for one of the most obvious ‘paralinguistic events’, namely laughter. Gaussian Mixture Models were trained with Perceptual Linear Prediction features, pitch&energy, pitch&voicing and modulation spectrum features to model laughter and speech. Data from the ICSI Meeting Corpus and the Dutch CGN corpus were used for our classification experiments. The results showed that Gaussian Mixture Models trained with Perceptual Linear Prediction features performed best with Equal Error Rates ranging from 7.1%-20.0%.