Voice-activated digital aides are making quite a splash across the globe, debuting in homes, cars, smart watches, computers and mobile phones. Usage of the speech recognition range from realms of public transportation, marketing, HR and finance in order to bring down business costs, thereby simplifying outdated processes and enhancing overall effectiveness. With notable advancements and innovations in the natural language understanding as well as speech accuracy rates, the new technological improvements have resulted in increasing appetite for companies that are constantly working on developing voice-enabled products and experiences that go beyond the private domain.
Liopa is a specialist based on BELFAST technology and has recently launched the world’s first ever automated lip reader. On an initial note, this automated lip reader will be utilized for preventing ‘spoofing’ in facial recognition systems as these systems experience the risk of compromise from videos and images that are displayed by imposters. The initial application is known as LipSecure, which is currently undergoing commercial trials with several facial recognition firms.
Highlights on LipSecure
The technology of Liopa is mainly dependent on VSR (visual speech recognition) and also analysis the lip movements of a speaker in order to decipher as to what the speaker is trying to convey. Advanced and innovative techniques based on automated intelligence are being utilized on any device that holds a standard camera. Several researchers have been stating that since the last decade, demand for VSR systems have grown exponentially mainly due to the rising usage of voice for driving applications such as Alexa, Cortana and Siri.
Superior Performance of Visual Speech Recognition in Lab Setting To Benefit Demand & Supply
Visual speech recognition has been showcasing superior performance in lab settings; however several difficulties are expected to come up with its launch in the real world and on mobile devices as well. The notable point here is that this new technology, LipSecure can deal with poor resolution and speaker head movement that varies in different lighting conditions. The company is expecting that this first launch of the visual speech recognition service would be highly beneficial for the future profit margins of the company.
The new and innovative technology of Liopa, LipSecure, is the resulting product of more than 50-man years of study in visual speech recognition, which has been conducted by Queen’s University. The initial application of LipSecure is expected to support a small vocabulary with possibilities of expanding more. Apart from this, by 2019, Liopa is planning to launch a communication tool that can be highly beneficial for patients experiencing difficulties owing to impaired speech. The company also mentioned that it will be embedding this technology across several voice-driven applications all through 2019.
Visual speech recognition as well as the AI (artificial intelligence) behind the innovation is expected to get more sophisticated going forward. The industry has already been saturated with various companies that are experimenting with their services and products consisting of digital voice assistants.