Classification of social laughter in natural conversational speech

• We observed several types of laughs in a natural speech corpus, and two predominant types of laughter (social vs. sincere) were categorized from a data manual examination of the data.
• Global prosodic and laughter-specific acoustic features were extracted for the two types of laughter. These parameters were analysed by Principal Component Analysis and Classification Trees to reduce the number of parameters.
• A Support Vector Machine was trained and tested using seven important features, and total classification accuracy was confirmed to be at least over 84 with unseen test material.

We report progress towards developing a sensor module that categorizes types of laughter for application in dialogue systems or social-skills training situations. The module will also function as a component to measure discourse engagement in natural conversational speech. This paper presents the results of an analysis into the sounds of human laughter in a very large corpus of naturally occurring conversational speech and our classification of the laughter types according to social function. Various types of laughter were categorized into either polite or genuinely mirthful categories and the analysis of these laughs forms the core of this report. Statistical analysis of the acoustic features of each laugh was performed and a Principal Component Analysis and Classification Tree analysis were performed to determine the main contributing factors in each case. A statistical model was then trained using a Support Vector Machine to predict the most likely category for each laugh in both speaker-specific and speaker-independent manner. Better than 70% accuracy was obtained in automatic classification tests.