VISUAL SPEECH RECOGNITION

Deciphers speech from lip movement
State-of-the-art deep learning

Whitepaper “Introducing Visual Speech Recognition"
Read how VSR improves the performance of voice-first services in noisy, real world environments
Get the whitepaper...
Discover the story behind Liopa
Liopa’s mission is to develop an accurate, easy-to-use
& robust Visual Speech Recognition (VSR) platform
FIND OUT MORE...
OVERVIEW – VSR APPLICATIONS

Liopa’s Visual Speech Recognition has various application use cases.

Voiceless Speech Recognition

Communications aid for people who have lost the ability to speak:
  • Smartphone-based
  • Analyses lip movements to decipher phrases
  • Configurable vocabularies supported.

Transforming the Voice UI

Improving accuracy of speech recognition. Making voice-driven applications better:
  • Virtual Assistants – Siri, Cortana, Alexa
  • In vehicle Voice Activation
  • Smart Home device control.

Liveness Detection

Improved online and mobile User Authentication for enhanced security:
  • ensuring a real person is present
  • anti-spoofing for Facial Recognition
  • alternative to CAPTCHA.
Technology
with Liopa LipRead

Liopa has created a novel, robust and convenient VSR platform, known as LipRead. Specifically, the Liopa technology can determine speech by analysing the movement of a user’s lips as they speak into a camera. These lip movements are known as visemes and are the visual equivalent of a phoneme or unit of sound in spoken language. The Liopa technology requires no additional hardware and will work on any device with a standard forward facing camera (e.g. smartphone, tablet, laptop, desktop, in-vehicle dashboard etc.).

VISUAL SPEECH RECOGNITION (VSR)

Liopa’s VSR – LipRead – is video only & not affected by poor audio quality and background noise.

IMPROVES ACCURACY

LipRead improves word accuracy in real-world/noisy environments to offer seamless, intuitive language-processing accuracy for enhanced voice user interface.

ENHANCED QUALITY & USABILITY

LipRead can enhance the quality and usability of the Voice UI in shared offices, on the move, across the production line or at home.

AI INTELLIGENCE

LipRead employs a proprietary Machine Learning approach using Deep Learning & can be ‘intelligently’ integrated with ASR technology using dynamic weighting algorithms.

NEWS
Check Liopa’s latest developments …
Professor Gerasimos Potamianos

WORLD RENOWNED AUTHORITY IN SPEECH RECOGNITION, PROFESSOR GERASIMOS POTAMIANOS, JOINS LIOPA

Liopa, the automated lip reading company, boosts its executive team with the appointment of Prof Potamianos as Technical Strategy Advisor. Liopa is excited to announce that Professor Gerasimos Potamianos has joined Liopa as Technical Strategy Advisor. Prof Potamianos, who is based at the University …

Read More >
Home 4

LIOPA’S PATIENT/CARER COMMUNICATION AID SHORTLISTED FOR TWO AWARDS

LIOPA is delighted to announce that SRAVI, its patient/carer communication aid based on AI-based Automated LipReading, has been shortlisted in the FORWARD HEALTHCARE AWARDS (Digital Patient category) and the Health Tech Awards 2019 (Most Promising Pilot category). Working along with …

Read More >
Home 5

LIOPA LAUNCHES VISUAL SPEECH RECOGNITION WHITE PAPER WITH OPUS RESEARCH

“Visual Speech Recognition” (VSR) has the catchy ring of a game-changing oxymoron, like “Virtual Reality” or “Artificial Intelligence.” All three are self-contradicting concepts that promise to prove invaluable as individuals, enterprises and government agencies try to take charge of unprecedented …

Read More >
BLOG

Read our BLOG for our views on VSR and ASR …

Home 6

In-vehicle voice activation – room for improvement?

Background  In-car speech recognition technology enables drivers to interact with a multitude of useful applications using their voice. Drivers can invoke navigation applications, voice calls, messaging applications, play music, query fuel consumption & set driving modes by simply speaking commands.  Improved road safety has been the primary motivation for the deployment of speech recognition systems in …

Read More >
Home 7

Biometric Authentication & Spoofing

(This guest article was originally posted in Biometric Technology Today). Today’s best user authentication systems are multi-factor. Users are verified by using –  something they know (e.g. a pin or password)  something they have (e.g. a key fob)  something they are (biometric authentication).  The “something they are” factor provides a very …

Read More >
Home 8

We’re developing an AI based platform to allow the hard of hearing to stay connected to the world around them

Read More >
Home 9
Home 10
Home 11
Home 12
Home 13

Signup for our newsletter!

WordPress Lightbox Plugin
Scroll to Top