Gears of War 4 creators first to use Edinburgh spin-out’s SGX software

More than 35,000 lines of dialogue in the Gears of War 4 game are animated by SGX software developed by University of Edinburgh spin-out Speech Graphics 

The company behind critically acclaimed video game Gears of War 4 has become the first to use groundbreaking SGX software developed by the University of Edinburgh spin-out Speech Graphics.
The Coalition, which is owned by Microsoft, is the first company to license the software, which generates facial animation from audio, to animate more than 35,000 lines of dialogue in the Gears of War 4 game. gears4_squad
Edinburgh-based Speech Graphics already has an international reputation for extraordinary advances in audio-driven animation and motion technology, providing facial animation for the video games industry and working with multinational companies and global artists, such as Warner Brothers and Kanye West.
The award-winning firm has also recently licensed its SGX software to a further three global studios, news of which is expected to be released in the new year.

According to software afficionados, SGX, which is the result of five years of research and development by Speech Graphics, marks a step change in the games sector by bringing the quality of in-game animation close to the quality of handcrafted cut-scene animation. 
SGX makes it possible for video game studios to execute large batches of facial animation of thousands of lines of dialogue in-house, using only audio recordings, without needing to outsource to specialists.gears4_marcus_closeup_4k
It also delivers an immersive experience for the gamer by processing audio files and transcripts into facial animation, creating audio-generated facial animation that is high-quality and scalable across large volumes of dialogue.
Michael Berger, CTO and co-founder of Speech Graphics, explains: “Automatic, accurate lip sync is one of the holy grails of computer facial animation.  Our task is to create the impression that the animated face you see is the source of the sound you hear.  This illusion is notoriously difficult to achieve: the movements of speech are fast, complex and subtle and the viewer is highly sensitive to any mismatch between face and the voice.
David Coleman, Animation Director of Gears of War 4, commented: “Speech Graphics provided us with a robust system for automatically creating quality facial animation for the many thousands of lines of gameplay dialogue in Gears of War 4. We found the people at Speech Graphics to be very responsive and helpful in us achieving our goals.”
“SGX goes beyond good lip sync. Speech contains energy and emotion, and that too can be decoded from the voice and synchronized in the face. Using all available acoustic information, our algorithms drive not just the mouth but the entire face from audio input, from syllables to scowls.”
Speech Graphics says SGX delivers accurate and expressive facial animation. Emotional impact comes through very strongly in both the upper and lower face. Speech Graphics technology captures the intensity of every syllable and animates eyebrows, eyes, lips, jaw, cheeks and even tongue. 
The software is said to use a unique fusion of expertise in speech technology and computer animation found nowhere else in the world.
Meanwhile, the Speech Graphics team brings together decades of research into machine learning, speech recognition, phonetics and computer graphics to solve what is an interdisciplinary problem.
Speech Graphics delivers pioneering facial animation technology to the entertainment industry, working with clients such as Warner Brothers and Def Jam Recordings. Based on over 20 years of R&D in speechtechnology and procedural facial dynamics, its software produces high-quality facial animation from audio alone, with no need for motion capture.
The company spun out of the University of Edinburgh’s world-renowned School of Informatics in 2011 under the leadership of founders Michael Berger and Gregor Hofer, and game industry veteran Colin Macdonald.
It’s now on track to become the main provider of lip-sync and facial animation – a sector forecast to reach over $500 million (£375m) – to the global video game market.
Speech Graphics currently employs eight staff and has plans to recruit three more in the year ahead.
Sponsored by
Hannah Hamilton, who is a former Fife College student, is a reporter and assistant content editor for Scotland B2B, specialising in B2B news and features. She can be contacted via