Recognizing Emotions in Dialogues with Disfluencies and Non-verbal Vocalisations

We investigate the usefulness of DISfluencies and Non-verbal Vocalisations (DIS-NV) for recognizing human emotions in dialogues. The proposed features measure filled pauses, fillers, stutters, laughter, and breath in utterances. The predictiveness of DISNV features is compared with lexical features and state-of-the-art low-level acoustic features. Our experimental results show that using DIS-NV features alone is not as predictive as using lexical or acoustic features. However, adding them to lexical or acoustic feature set yields improvement compared to using lexical or acoustic features alone. This indicates that disfluencies and non-verbal vocalisations provide useful information overlooked by the other two types of features for emotion recognition.