Pioneering Facial Animation Technology

Speech Graphics’ software produces high-quality facial animation from audio alone, with no need for motion capture.

In the sound of speech there is a wealth of information about what the speaker was doing when he or she made the sound – including the movements of the mouth as it produced the sound, and the energetic state of the speaker, from which we can deduce facial expression. This is a type of “inverse problem” – reconstructing the cause (the speaker) from the observed effect (the sound). As the first step of this inversion, Speech Graphics’ specialised speech analysis algorithms discover acoustic events in the audio, and trace those to back to appropriate kinds of movements in the mouth and face.

Based on over 20 years of R&D in speech technology and procedural facial dynamics, Speech Graphics spun out of the University of Edinburgh’s world-renowned School of Informatics in 2010, under the leadership of founders Michael Berger and Gregor Hofer and game industry veteran Colin Macdonald. Speech Graphics has won several awards for its speech-driven animation technology, including the prestigious John Logie Baird Award for innovation.

Speech Graphics’ technology is currently used in the entertainment industry; their clients include Warner Brothers and Def Jam Recordings. They have also developed early proof of concept relationships with strategic partners in the banking and healthcare sectors.

David Ovens