Across multiple sectors training programmes aim to help learners improve their communication skills. It is well recognised that non-verbal ‘social signals’ play an important role in communication effectiveness. Previous research in the social signalling domain meticulously observed hours of videos and conducted observational studies to identify these social signals. This resulted in subjective inferences about human emotions. The aim of the current research is to investigate whether social signals can be detected and trained using automated technology in a person-to-person training context in three stages; exploratory stage, feedback design stage and an experimental stage. This research will allow trainers to provide objective feedback to trainees about their performance with a clear criterion. This research will also explore the best way to feedback signals detected and whether this is effective and actionable. Further long-term benefits of this research might contribute to the eventual development of a training avatar.