The company’s software-based enCaption solutions provide accurate closed captioning for both live and pre-recorded content in near real-time. The enCaption4’s new speech-to-text engine takes this accuracy to an unprecedented new level, leveraging breakthroughs in machine learning technology to develop a deep neural network approach to voice recognition.

This accuracy is further enhanced by a dictionary database three times larger than previous ENCO enCaption solutions, while integration with popular newsroom computer systems (NRCS) takes advantage of news scripts and rundowns to learn and validate the spelling of local names and terminology. The result is greater automated captioning accuracy across a full array of program types, ranging from fast and dynamic sports play-by-play to slower-paced informational shows.

The new enCaption4 also improves end-to-end captioning latency, cutting in half the time between spoken words and their corresponding on-screen caption representation. Generating captions in live, real-time environments faster than human stenographers, the new software improves the viewing experience for hearing-impaired audiences with much closer synchronization between captions and actual speech.

The addition of a cloud-based offering to the enCaption family enables users to minimize on-premises equipment while leveraging the vast scalability, resource availability and multi-location collaborative benefits of public cloud platforms.

Ideal for meeting captioning needs around the globe, enCaption4 currently supports 28 international languages. Beyond television broadcasters and media businesses, the increased performance and deployment flexibility of enCaption4 offer significant benefits for organizations including corporate enterprises, financial institutions, educational environments and government agencies, all of which may produce significant volumes of video content requiring captions.

The new enCaption4 is now available. The existing enCaption3 system will continue to be available and actively developed, becoming ENCO’s entry-level automated captioning solution.

In October, Enco Systems announced it had acquired a patent that specifically applies to providing automated captioning by using speech-to-text. The United States patent, number 7047191B2, entitled: Method and System for Providing Automated Captioning for AV Signals, expands ENCO’s intellectual property for captioning technology and methods that help broadcasters automate and accelerate speech-to-text translation to deliver open or closed captions.