Intermediary Fuzzification in Speech Emotion Recognition

摘要

Affective systems are getting increasingly more attention from researchers and high-tech companies in order to enable the acknowledgment or adaptation to a user’s mood. Emotion classification is typically a hard problem due to the number of subtle cues which are present in human facial and body expressions, or in voiced utterances. Another critical factor is that typically used models tend to map emotions into all-or-nothing regions with artificially sharp divisions among them, a view which is rather unsupported in the field of psychology and human behavioral analysis. In this paper we propose the inclusion of an intermediary fuzzy layer in a VGGVox-based NN, whose aim is to deal with the inherently foggy transitions between emotional states. This neuro-fuzzy model was trained and evaluated against four emotional speech databases and has shown improvements in the classification performance over a non-fuzzy counterpart. Observed performances were also on-par or above those of other current state-of-the-art techniques.