XL8 Unveils Real-Time AI-Based Interpretation App for Zoom Meetings

 XL8 Inc., a Silicon Valley tech company that provides AI-powered machine translation technology optimized for media content and dialogues, on Feb. 21 announced it is expanding its interpretation engine into the online video conferencing world, with a new app delivering accurate real-time translation during multi-language Zoom meetings. 

“Zoom is now a permanent part of our lives for work and social interaction,” said Tim Jung, CEO of XL8. “It’s an all-too-common scenario where one participant may only speak French or Vietnamese while the host is a primarily English speaker, for example. The interaction would be limited at best, and when there are multiple participants each speaking a different language it can get unwieldy.

“Our easy-to-use app removes that language barrier and lets participants have more productive online meeting experiences without worrying about missing key words.”

The new Zoom Integration is based on the XL8 Interpret platform capabilities, the same core translation technologies used to power the company’s EventCat platform for live event interpretation and live subtitling and MediaCAT platform for media content localization.

The XL8 engine covers more than 20 languages and 355 language pairs. While this list already covers most of the languages frequently requested by users, XL8 is adding new languages to the stack.

“What sets this apart from competitive offerings is we are doing real-time translation and enabling multiple languages in the same software suite, and all based on the colloquial speech patterns people use every day,” said John Butterworth, VP of sales engineering at XL8. “It’s an ideal solution for any sized organization with distributed employees or even for individual users who often communicate with others who speak different languages.”

To use the new app, users need an XL8 account, which can be created on any of the XL8’s products. A few invited users from the waitlist will soon start getting an invitation email to enable the app for their Zoom account. Once enabled, the app will appear in the lower-right side of the user’s Zoom window under “Apps.”

After enabling the app, the process is slightly different for hosts and participants. The host first needs to select the language the host will be speaking as a participant and also all the languages that will be spoken during the meeting. Participants simply select their own language to join the session. Once the host initiates the app, a bot will automatically join and begin recording the meeting for interpretation.

The new app will be launched as Beta and be made available to the general public in March. 

Machine Technology Translation Provider Launches Newest Sets of ‘Context Awareness’ Language Pairs

 XL8 Inc., a Silicon Valley tech company that provides AI-powered machine translation technology optimized for media content, Oct. 24 announced its newest sets of Context Awareness (CA) language pairs.

XL8’s language pairs are designed to increase the translation and subtitling accuracy for localization service providers (LSP). 

XL8 says its language pairs deliver new workflow efficiencies for LSPs in terms of less post-editing work and a 32% reduction in project delivery times. These newest models bring the company’s total number of context-aware language pairs to 40. By the end of 2022, all of XL8’s 73 engines will be context-aware.

XL8’s application of context awareness in its machine translation technology enhances the immersive experiences for audiences watching live or pre-recorded streaming or broadcast content. XL8’s context awareness engine does what was previously the sole domain of humans, accurately considering the context of a conversation and evaluating the subtle differences of gender, slang, formalities, multiple word meanings, and other language intricacies.

A third-party committee of content localization service providers tested the new models for translating from English to Latin Spanish using several categories of programming (such as sci-fi, comedy, food, travel, drama). The tests were conducted with and without the XL8 context awareness model applied. While both sets performed well, the accuracy of XL8’s CA model averaged 95.5% and the normal model average was 91.2%.

Overall, XL8 says, the context awareness model was more accurate regarding gender and formality consistency among multiple subtitles. While both performed well at providing coherent sentences, even when faced with misspelled words or odd phrasings, the context awareness model was more accurate with certain categories like food, where dishes were described in extreme detail with long lists of ingredients.

XL8 was founded in 2019 by technical executives from Google and Apple, both with advanced degrees in Computer Science from Columbia University. XL8 says its advanced technology allows significantly more-efficient workflows by providing inline editing, automated media transcription with time coding, automated subtitling, synthesized voice dubbing, real-time meeting interpretation, and live subtitling.