Skip to main content

EEG Video Unveils Core Models for Lexi Captioning Solution

EEG Lexi Core Models
(Image credit: EEG)

FARMINGDALE, N.Y.—EEG Video has announced the availability of Core Models for its Lexi automatic caption solution. 

The new feature expands on the usefulness of EEG’s Topic Models system to enable accurate display of custom vocabulary and phrases. It allows Lexi to recognize topics, immerse itself in distinctive vocabulary and observe context by absorbing relevant web data unique to each implementation, the company said.

“It only takes one look at off-the-shelf speech-to-text transcripts to realize that customization and updates are a critical task, but one that many end users are limited in time and experience to effectively perform on their own,” says Bill McLaughlin, vice president of Product Development for EEG Video.

“EEG’s experts have the deep data curation skills needed to update AI models effectively and efficiently. This leverages the shared needs of our many AI captioning customers to produce Core Models, dramatically reducing the customization requirements of individual customers in common applications,” he said.

With Topic Models, Lexi can perform in real time with a high degree of accuracy by addressing poor recognition of topic-specific vocabulary. This includes less common proper nouns, including names of people, places and products, the company said.

These models also enhance recognition of entire phrases, jargon, vocabularies or speaking styles that are typical in a certain context but not another, such as during a baseball telecast, EEG Video said.

Some commercial off-the-shelf speech-to-text engines do not recognize certain words and phrases, such as “coronavirus” or “COVID-19,” offering substitutions like “culvert” for the latter,  the company said. Eliminating these errors is critical for breaking news broadcasts to maintain the credibility of captions and to improve audience engagement and satisfaction, it said.

After three years of providing AI captioning for a wide variety of events and media, EEG’s AI team has distilled common vocabulary training cases into a set of Core Models. Customers also can build their own individual Topic Models on top of an EEG Core Model, it said. 

As EEG continues to evolve and add to the Core Model, the derived individual user models are also automatically updated to merge individual and Core changes, it said.

Current EEG Core Models exist in English for:

  • Headline News (United States-focused): more than 15,000 entities and phrases;
  • Sports: Baseball (MLB-focused): more than 10,000 entities and phrases; 
  • Christian Broadcasting: more than 15,000 entities and phrases; 
  • Legislative and Municipal Sessions: more than 1,000 entities and phrases; and 
  • Weather (United States focused): more than 1,000 entities and phrases. 

More information is available on the company’s website

Phil Kurz

Phil Kurz is a contributing editor to TV Tech. He has written about TV and video technology for more than 30 years and served as editor of three leading industry magazines. He earned a Bachelor of Journalism and a Master’s Degree in Journalism from the University of Missouri-Columbia School of Journalism.