Lens on Visual Speech Recognition Startup: Liopa

Liopa: Lip reading finally deciphered

Ireland based Liopa (Irish for lips) has raised $1 million from investors such as AI Seed and Co-Fund NI to commercialize an innovative lip reading platform LipREAD which can analyze lip movements, decipher words and phrases. As voice takes over keyboard and mouse and voice assistants like Siri and Alexa are making inroads into our day to day lives, the implication of this product can be profound. The efficacy and accuracy of voice driven assistants and other voice activated applications can significantly improve, especially in an environment with background noise. LipREAD is initially positioned as a supporting system for audio speech recognition systems that face accuracy issues in noisy environments.



According to Liopa: The Liopa VSR technology is based on the principle of Viseme analysis. A viseme is a generic facial image that can be used to describe a particular sound. A viseme is the visual equivalent of a phoneme or unit of sound in spoken language. Using visemes, the hearing-impaired can view sounds visually – effectively, “lip-reading” the entire human face."

As large players in the voice application space continue to improve their offerings, startups like Liopa can become attractive acquisition candidates for companies like Amazon and Google. The commercial application of this technology can be immense, from in-vehicle systems to systems operating in other noisy environments such as retail.

So, we can say that technology has once again mastered the art that humans have been trying to practice for centuries, i.e, reading people’s lips!