Print Email Facebook Twitter Automatic detection of laughter Title Automatic detection of laughter Author Truong, K.P. van Leeuwen, D.A. TNO Defensie en Veiligheid Publication year 2005 Abstract In the context of detecting paralinguistic events with the aim to make classification of the speakers 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%. Subject Automatic speech recognitionLaughterAutomationError correctionLinearizationLinguisticsMathematical modelsModulationSpeech analysisWhite noiseEmotional stateGaussian Mixture ModelsModulation spectraParalinguistic eventsGesture recognition To reference this document use: http://resolver.tudelft.nl/uuid:2ee5369f-67a6-4e3f-868e-ee2b9893bcdc TNO identifier 15958 Source 9th European Conference on Speech Communication and Technology, 4 September 2005 through 8 September 2005, Lisbon,, 485-488 Document type conference paper Files To receive the publication files, please send an e-mail request to TNO Library.