Emotion Dependent Facial Animation from Affective Speech
arXiv:1908.03904
The paper proposes a two‑stage deep learning system that first classifies speech into seven emotions and then generates corresponding facial shape animations, showing improved performance over a universal model.
Abstract
In human-to-computer interaction, facial animation in synchrony with affective speech can deliver more naturalistic conversational agents. In this paper, we present a two-stage deep learning approach for affective speech driven facial shape animation. In the first stage, we classify affective speech into seven emotion categories. In the second stage, we train separate deep estimators within each emotion category to synthesize facial shape from the affective speech. Objective and subjective evaluations are performed over the SAVEE dataset. The proposed emotion dependent facial shape model performs better in terms of the Mean Squared Error (MSE) loss and in generating the landmark animations, as compared to training a universal model regardless of the emotion.