Baton LipSync and Baton Captions from Interra Systems use automation to, respectively, solve critical lipsync issues and to bring “simplicity and cost savings to the creation, management and delivery of captions”, according to the company.
Baton LipSync, an automated tool for lipsync detection and verification, leverages machine learning technology and deep neural networks to automatically detect audio and video sync errors. It should enable users to accurately detect audio lead and lag issues in media content in order to improve quality.
“Lipsync errors are annoying, distracting and negatively impact overall viewing experiences,” said Anupama Anantharaman, Interra Systems’ VP of product management. With Baton LipSync, “we’re extending our video quality control expertise to help address the difficult problem of audio-video sync using advanced image processing and machine learning technologies. In addition to solving the problem of detection, accompanying debug information and comprehensive reporting will go a long way in assuring audio-video sync accuracy and helping our customers to deliver a more satisfying viewing experience.”
The application can perform facial detection, facial tracking, lip detection and lip activity detection. Sync errors can be debugged further in the Baton Media Player through an interface that plots out-of-sync audio and video errors on a skew timeline for better visualisation. After errors are detected, Baton LipSync provides a comprehensive report of all the lipsync issues. Available content can be checked in any language independent of the region and area.
Baton Captions automates all kinds of captioning, allowing users to address requirements from caption generation to QC, auto corrections, review and editing. It uses automatic speech recognition technology, and reports on any drop or inaccuracy in captions and audio, as well as compliance issues, providing broadcasters with automated options for correcting alignment and text.
Captions can be checked against actual audio essence, corrected and exported to any industry-supported caption format. It can add accurate time to dialogues in scripts, resulting in faster, more efficient caption generation.
Through web-services-based API support, Baton Captions can easily be integrated with third-party tools, and can be deployed on premises or in the cloud.
Interra’s overall Baton QC system has also been updated, including enhancements in IMF and HDR checks, usability, as well as new additions to audio language detection.
There is also an updated version of the company’s Baton Media Player, which includes support for overlaying timecode information on video, performance enhancements in J2K playback, the option to export a video clip without re-encoding, improvements in real-time playback, support for playback of growing Material eXchange Format (MXF) files and more.
Interra Systems is currently running a series of free educational webinars focusing on its latest quality control, monitoring, analysis and classification systems, particularly Baton LipSync and Baton Captions.