ENCO's AI-Powered enTranslate System To Debut At InfoComm 2019

AV professionals in all types of organisations are constantly striving to make their content accessible and understandable to more viewers, whether in-person or online. Extending the company's rich history of innovation in automated media captioning to multi-language translation, ENCO's new AI-powered enTranslate system will make its AV industry debut in booth 5491 at InfoComm 2019.

enTranslate combines the powerful speech-to-text engine from ENCO's patented enCaption open and closed captioning solution with advanced translation technology powered by Veritone, enabling automated, near-real-time translation of live or pre-recorded content for alternative-language captioning, subtitling and more.

Helping make AV content understandable to viewers who don’t speak its original language, enTranslate offers an easy and affordable solution to automatically translate live presentations and recorded content such as training and learning videos. Users can choose to embed translated captions in short and long-form VOD content for subsequent on-demand consumption, or to display live, open-captioned subtitles on local video displays to assist in-person attendees. enTranslate supports 46 languages including English, Spanish, French and more.

"As media content has become an intrinsic part of modern communications across all vertical markets, AV professionals are increasingly challenged to ensure that even non-native-speaking viewers and participants can easily comprehend the material," said Ken Frommert, President of ENCO. "For example, schools may want to better serve their ESL (English as a Second Language) students, while churches look to clearly convey their message to multi-cultural congregations and local governments strive for transparency to diverse constituents. Traditional manual translation services can be prohibitively expensive, but enTranslate makes live translation both practical and affordable for all types of organizations."

enTranslate builds on the highly-accurate, machine learning powered speech recognition core first implemented in enCaption to interpret incoming live or file-based audio, then feeds the resulting text to its advanced translation engine. Blending artificial intelligence with sophisticated linguistics modelling, enTranslate uses a Neural Machine Translation methodology to provide high-quality translations based on the context surrounding the current words and phrases.

enTranslate offers both live and offline translation, and can be deployed on-premises or in the cloud. For file-based applications, audio or video clips can be easily ingested into the system and captioned with translations in any supported language, enabling users to quickly and affordably process large libraries of previously recorded content.