Online Content Toolkit (OCTO)

Aims

How can we help journalists find and create video clips for reuse online and on social media?

The Online Content Toolkit, or OCTO, is a project exploring media editing, repurposing and augmentation based on the results of intelligent analysis.

We're using a variety of "enrichment processes" - such as automatic speech recognition and shot detection - on BBC News production content and aggregating the results in a central repository. This forms the basis of a number of specialised tools that can be used either individually or composed together into workflows.

At present the majority of our efforts are focused on the use of automatic speech recognition to generate transcripts of speech content. We're running a subset of new content in BBC News' main television and radio production systems through the open-source Kaldi engine and building prototype tools based on the results. Particular areas of interest include the automatic generation of subtitles and repurposing of video content for users on low-bandwidth connections.

How it works

Results

• We have a prototype version for BBC producers to use while we wait to transfer it to a product team.