Google's DeepMind AI binges on TV to master lipreading
After digesting 5,000 hours of TV programs, the AI system outperforms a professional lip-reader.
Artificial intelligence could soon make asking Google Assistant a question in public a little less awkward.
A project by the University of Oxford and UK-based DeepMind, owned by Google parent company Alphabet, trained an artificial-intelligence system to read lips by analyzing 5,000 hours of TV programs, reported New Scientist on Monday.
University of Oxford and DeepMind researchers trained the AI system on six different TV programs that aired between January 2010 and December 2015. After training, the AI was capable of deciphering 46.8 percent of words without any error from 200 randomly selected clips. A professional lip-reader attempted to annotate the same set, but was only able to decipher 12.4 percent of words without any error.
Lip-reading AI would likely be used for consumer applications including improving accuracy of voice recognition systems and silent dictation, New Scientist reported.
This isn't the first AI system from DeepMind to best a human. In March, a DeepMind AI program dubbed AlphaGo beat world champion Lee Sedol in Go, an ancient and complex board game in which strategy and tactics collide with intuition and cunning. DeepMind also this week unveiled a partnership with the UK's state-run National Health Service to provide an AI-based phone app called Streams that will help doctors find at-risk patients. Some have raised concerns about partnership, which gives DeepMind access to vast swaths of patient data collected by the NHS.