LivingLens Adds Speech-to-Text Capability

In the UK, video data mining specialist LivingLens has added machine speech recognition capabilities to its platform, to offer a near real-time 'speech to text' service. It has also added a module through which videos can be searched by consumer sentiment and activity.

LivingLens has bases in London and Liverpool. The firm's app platform enables consumers to capture, edit and share videos, whose content can then be analysed using software that intelligently searches every spoken word in 'any language'. The addition of speech-to-text capabilities, available in four languages, means the platform will now provide a massive scale processing and live 'in-the-moment' offering, according to the firm.

The new version also includes a multi-layer search upgrade, through which users can search video by activity and sentiment, drilling down to information about what consumers are physically doing, and their emotional reactions at specific points in the video. These search capabilities are supported by LivingLens Intelligent Synonym, which the firm says provides a new way for clients to integrate their business language into the video content, and removes the need to spend time tagging videos. All the new capabilities are also available via API's.

David Woods (pictured), co-founder and COO, comments: 'Over the last twelve months we have put together a world-class development team, which has culminated in this release. This new version, the first of a number of exciting developments planned for 2016, will allow the industry to use video at scale across all forms of video, turning it into a data asset in its own right'.

Web site: www.livinglens.tv .

All articles 2006-23 written and edited by Mel Crowther and/or Nick Thomas, 2024- by Nick Thomas, unless otherwise stated.