Nexidia QC Automates Manual Processes
ATLANTA —Nexidia, developer of dialogue and audio analysis products and technologies for optimizing audio and video media, has launched Nexidia QC, a software tool for automated closed caption and video description verification, closed caption alignment and language identification for broadcast and IP workflows.
“The digital assets broadcasters work with are becoming more and more complex, especially on an international level, where an asset might have mezzanine files for 20 different languages,” said Drew Lanham, senior vice president and general manager of Nexidia’s Media and Entertainment division. “Language and caption quality impacts the entire delivery chain. There have been many quality control products available for video analysis, audio quality, loudness and more, but nothing for language and caption verification until now.”
Nexidia QC verifies quality automatically at every stage from ingest to playout to ensure that the right caption file appears against the right media in the right language, and that it is properly timed.
In order to verify the video description, Nexidia QC analyzes both the program audio and the secondary audio program. The software compares the program audio tracks against one another, identifying all segments in which the audio is not identical and returning a video description coverage score. It also identifies the primary spoken language of the program audio and the SAP.
To determine closed caption compliance, the software first identifies the primary spoken language of the program audio and the caption text. If the languages match, the application verifies that the caption text matches the program audio and whether the caption timing is correct. Nexidia QC checks the level of caption coverage for the program based on the difference between the segments with accurate caption information and voice activity, and evaluates the closed caption coverage score.
Nexidia QC can also repair misaligned caption files. It compares the time codes of the words spoken in the audio track to the time codes in the caption file. Adjustments are made to so that the captions are aligned with the spoken words, returning a new caption file ready for distribution.