VISUAL SPEECH RECOGNITION
Deciphers speech from lip movement
State-of-the-art deep learning
OVERVIEW – VSR APPLICATIONS
Liopa Visual Speech Recognition has three main application use cases.
Voiceless Speech Recognition
- Smartphone-based
- Analyses lip movements to decipher phrases
- Configurable vocabularies supported.
Transforming the Voice UI
- Virtual Assistants – Siri, Cortana, Alexa
- In vehicle Voice Activation
- Smart Home device control.
Liveness Detection
- ensuring a real person is present
- anti-spoofing for Facial Recognition
- alternative to CAPTCHA.
Technology
with Liopa LipRead
Voice is now perceived as the future of the User Interface, ultimately replacing keyboard, mouse and touchpad. Today’s voice-driven UIs (e.g. Alexa, Siri) depend on Audio Speech Recognition (ASR) technology. But ASR accuracy & user experience can be severely impacted by background noise. Watch a quick overview.
NEWS
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 …
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 …
MEET THE TEAM: DR HELEN BEAR, SENIOR RESEARCH & DEVELOPMENT ENGINEER
I’ve recently joined Liopa as Senior Research and Development Engineer. My background is in lip reading and understanding visual speech signals. I’ve spent the last year at Queen Mary University of London conducting research into “Integrating sound and context recognition …
BLOG
Read our BLOG for our views on VSR and ASR …
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 …
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 …
