Researchers improve AI emotion classification by combining speech and facial expression data

Systems that can classify a person's emotion from their voice and facial tics alone are a longstanding goal of some AI researchers. Firms like Affectiva, which recently launched a product that scans drivers' faces and voices to monitor their mood, are moving the needle in the right direction. But considerable challenges remain, owing to nuances in speech and muscle movements. Researchers at the University of Science and Technology of China in Hefei claim to have made progress, though. In a paper published on the preprint server Arxiv.org this week ("Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio video Emotion Recognition"), they describe an AI system that can recognize a person's emotional state with state-of-the-art accuracy on a popular benchmark.