ENCO's enCaption3 is a fully automated, speaker independent speech recognition-based system.
ENCO Systems has released its next generation automated captioning solution for live or recorded video. Called enCaption3 R3, it is a real-time automated captioning system for television broadcasters that does not require special voice training.
The ENCO system consists of a rack-mount processor unit that provides a serial data stream (CEA-608), feeding a captioning encoder. The enCaption3 R3 solution allows broadcasters to serve their hearing impaired audience for a fraction of the cost of traditional captioning services and is always available for live and breaking news, weather, and events. It does not require any user intervention and automatically captions what is spoken, even if the talent goes off script. ENCO offers enCaption3 R3 in over 20 different languages.
As a fully automated, speaker independent speech recognition-based system, the enCaption3 captioning solution is not an ENR/prompter based system, nor is it a “re-speaking” system requiring live personnel to operate.
Linking enCaption 3 to an existing electronic newsroom system allows it to automatically access current and historical script information to build a local dictionary that leads to improved accuracy over time. Users can feed enCaption specific scripts for presentations, meetings or other productions. The enCaption 3 solution is not ideal for use where background noise is high or scoring or other musical elements are present mixed underneath spoken voices. When a clean audio feed and script material (used to build and maintain a local dictionary) is provided, enCaption 3 gets the job done reliably, accurately and at a significant cost savings.
You might also like...
KVM is more important now for broadcast-IP systems than it ever has been. As manufacturers turn to server based architectures private cloud installations have become more mainstream, requiring us to configure systems through traditional server control inputs, that is keyboard,…
Deluxe Entertainment Services Group has bought Sfera Studios and Sfera Labs to enhance its content localisation efforts. The new division is led by former Google Head of Global Language Services Derek McKellar.
If adding captions to your streaming content – whether it’s on-demand or live – feels daunting, you’re not alone. Both present new challenges that arise in step with fast-evolving formats and consumer tastes.
The SubtitleNext platform has the capability to dramatically improve caption and subtitling speed and efficiency, and it simplifies the processes throughout the entire work cycle.
Innovation has become a mantra for broadcasters, driven in part by the disruption of online content consumption and proliferation of video content sources which now number 1 billion globally by some counts. Innovation is seen as crucial for the very long…