Segmenting into Adequate Units for Automatic Recognition of Emotion-Related Episodes: A Speech-Based Approach

We deal with the topic of segmenting emotion-related (emotional/affective) episodes into adequate units for analysis and automaticprocessing/classification—a topic that has not been addressed ade quately so far. We concentrate on speech and illustrate promisingapproaches by using a database with children’s emotional speech. We argue in favour of the word as basic unit and map sequences ofwords on both syntactic and “emotionally consistent” chunks and report classification performances for an exhaustive modelling ofour data by mapping word-based paralinguistic emotion labels onto three classes representing valence (positive, neutral, negative),and onto a fourth rest (garbage) class.