Researchers from Google’s AI division DeepMind and the University of Oxford have used artificial intelligence to create the most accurate lip-reading software ever. Using thousands of hours of TV footage from the BBC, scientists trained a neural network to annotate video footage with 46.8 percent accuracy. That might not seem that impressive at first — especially compared to AI accuracy rates when transcribing audio — but tested on the same footage, a professional human lip-reader was only able to get the right word 12.4 percent of the time.

The research follows similar work published a separate group at the University of Oxford earlier this month. Using related techniques, these scientist were able to create a lip-reading program…

Continue reading…

Source: <a href="Google’s AI can now lip read better than humans after watching thousands of hours of TV« >TheOldReader