Speech and Vision Lab

  • Increase font size
  • Default font size
  • Decrease font size
Home Publications
Analysis of laugh signals for detecting in continuous speech
Research Area: Speech Analysis Year: 2009
Type of Publication: In Proceedings Keywords: Laughter detection, epoch, strength of excitation
Authors: Sudheer K., Sri Harish Reddy M., Sri Rama Murty K., B. Yegnanarayana  
   
Abstract:
Laughter is a nonverbal vocalization that occurs often in speech communication. Since laughter is produced by the speech pro- duction mechanism, spectral analysis methods are used mostly for the study of laughter acoustics. In this paper the significance of excitation features for discriminating laughter and speech is discussed. New features describing the excitation characteris- tics are used to analyze the laugh signals. The features are based on instantaneous pitch and strength of excitation at epochs. An algorithm is developed based on these features to detect laugh- ter regions in continuous speech. The results are illustrated by detecting laughter regions in a TV broadcast program.
Digital version