A Face-to-Face Neural Conversation Model
This work addresses the lack of non-verbal cues in AI dialog systems for more realistic human-computer interaction, though it is incremental as it builds on existing RNN encoder-decoder methods.
The authors tackled the problem of neural conversation models being limited to text by proposing a model that generates both verbal responses and facial gestures, trained on 250 movies, and showed improved naturalness in conversations through metrics and a human study.
Neural networks have recently become good at engaging in dialog. However, current approaches are based solely on verbal text, lacking the richness of a real face-to-face conversation. We propose a neural conversation model that aims to read and generate facial gestures alongside with text. This allows our model to adapt its response based on the "mood" of the conversation. In particular, we introduce an RNN encoder-decoder that exploits the movement of facial muscles, as well as the verbal conversation. The decoder consists of two layers, where the lower layer aims at generating the verbal response and coarse facial expressions, while the second layer fills in the subtle gestures, making the generated output more smooth and natural. We train our neural network by having it "watch" 250 movies. We showcase our joint face-text model in generating more natural conversations through automatic metrics and a human study. We demonstrate an example application with a face-to-face chatting avatar.