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. 

FARMINGDALE, N.Y.—EEG Video has installed a new feature into its Lexi Automated Captioning service, the Scheduling workflow that enables users to schedule, monitor and manage captioning jobs.

Lexi, or Lexi Local, users can use the Scheduling feature to program a future start and end time for automatic captioning. Recurring events can also be set up for regularly scheduled programming.

The Scheduling solution also offers Instances, which gives users the ability to create a template for easy duplication of settings across different sessions to specify the same language, topic models, access codes, caption appearance and more are uniform for each desired session.

Users of EEG’s Falcon Live Streaming RTMP Caption Encoder who utilize Lexi will also benefit from the new Scheduling feature, the company says.

“As the adoption of cloud-based automatic captioning increases, users expect these situations to integrate more permanently and smoothly into their day-to-day production,” said Bill McLaughlin, vice president of product development, EEG Video. “Lexi’s new capability further reduces the learning curve and time commitment to successfully deploy live automatic captioning.”

For more information, visit www.eegent.com.  

FARMINGDALE, N.Y.—EEG believes that knowing what is being talked about can help its Lexi automatic cloud-based live captioning platform perform more accurately. That is the idea behind the company’s new Topic Model technology, which enables Lexi to recognize topics, immerse itself in distinctive vocabulary and observe context through the absorption of relevant web data unique to an implementation.

Lexi users can select one of EEG’s developed topic models during the setup process; they can also create their own custom model by providing reference URL’s or other text data specific to a subject matter or location. Lexi takes the data and observes the context of the words and names to recognize where and how they are often used.

EEG claims that with Topic Models, Lexi’s accuracy exceeds that of its previous speech-to-text systems. 

FARMINGDALE, N.Y.—EEG’s is now offering closed captioning service from the cloud, announcing the launch of Lexi. This cloud-hosed service connects existing EEG closed caption workflows with Automatic Speech Recognition technology, including support for on-demand ASR closed caption delivery through EEG products for live and offline material.

Lexi provides real-time transcriptions for live workflows based on audio supplied from any iCap connected devices. For offline or non-live captioning, subscription access to Lexi is built directly into EEG’s Scribe Closed Caption Editor. EEG advertises that the Lexi is capable of delivering more than 90 percent accuracy for English and Spanish, and can be used as part of a hybrid approach, with Lexi data being automatically interspersed with existing captions from a teleprompter system and/or human captioner.

The model supports hardware HD-SDI closed caption encoders from EEG, Falcon streaming encoders, Alta transport stream software, third-party iCap integrations and proxy devices that links other third-party hardware caption encoders to iCap.

EEG will offer the Lexi service in “Solution” and “Emergency” tiers. The Solution Tier provides 24/7 live ASR captioning, while the Emergency Tier offers a few hours of service monthly as a live caption backup for emergencies.