PRODUCTS
At Speech Graphics we specialize in one of the holy grails of computer facial animation: automatic, accurate lip sync.
The SGX suite delivers high quality automated facial animation from audio on first pass, and gives you control to direct the resulting performance in line with your precise vision.
SG Com allows for real-time audio-driven facial animation for player-to-player avatar chat and a range of other applications!
The Rapport platform makes it easy to combine dialogue solutions with text-to-speech and speech recognition tools, to create and deploy interactive character experiences at scale, anywhere.
“Look mom, no hands!”
This is completely raw, automatic, audio-driven facial animation output from SGX into the Unreal Engine, with no manual intervention or editing of facial keyframes.
-
SGX
PRODUCTION SOFTWARE
Automate high-fidelity facial animation from pre-recorded speech. As seen in Halo Infinite, The Last Of Us: Part II, Resident Evil 8: Village, Shadow of Mordor, Gears of War 5, Shadow of the Tomb Raider, and many more…
-
SG COM
RUNTIME SOFTWARE
Animate live speech in real time.
Complete, accurate lip sync with tongue motion, and full-face movement including emotional expression, head bobs, blinking, and eye darts, in the cloud and on-the-fly.
-
RAPPORT
REAL-TIME PLATFORM
Turn marketing content into conversations to get players immersed in the story, characters and lore of your next release, to ramp up pre-orders.
Rising to the Challenge
Given audio, our task is to create the illusion 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 viewers are highly sensitive to any mismatch between the face and the voice. Our world-class pipeline incorporates powerful speech analysis and procedural animation techniques to achieve this illusion consistently, allowing animators to handle overwhelming demand for high-quality dialogue.
Exceeding Expectations
Speech Graphics 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.
Assembling the Brightest Minds!
This is an interdisciplinary problem and Speech Graphics has a unique fusion of expertise in speech technology and computer animation found nowhere else in the world. Our team brings together decades of research into phonetics, task dynamics, speech recognition, psychology, machine learning, computer graphics, physical models and more. And we have solved the problem of how best to apply our systems to real-world facial rigs.
