Speechmatics has launched Sasquatch, a new solution that uses automatic speech recognition to auto transcribe any speech in a video and add it as subtitles.
The company says the solution will enable companies to reach a larger audience with social video, including those with hearing impairment.
Sasquatch has been developed by Screen Systems and is powered by Speechmatics.
Once video content has been uploaded, the solution will automatically generate subtitles, giving them percentage scores for text accuracy, readability, coverage and layout. Sasquatch then demonstrates changes that will lead to higher quality subtitles. Users can choose how to present their subtitles, the speed in which they’re presented, and how they’re broken up on the screen.
“Sasquatch is about the empowerment of the individual. We believe that 100 per cent of media content should be captured – there’s absolutely no reason for it not to be,” said John Birch, strategy and business development manager at Screen Systems. “We know that there’s a very large community who are deaf but we’re also aware that there are people who can hear perfectly well who are situationally disadvantaged, like when they’re browsing social media at work.
“We’re not replacing anything, we’ve just created a new way of doing subtitling for social media content and it wouldn’t be possible without Speechmatics’ leading speech-to-text technology.”
Ian Firth, VP Products at Speechmatics, added: “Subtitling has only ever been possible with high-end, production systems and typically only used for broadcast content. As a business, we’re passionate about making all content accessible, so we’re delighted to be partnered with Screen Systems and integrated into Sasquatch. This partnership is a further affirmation of the quality of our speech engine, and we’re incredibly excited to see the benefits Sasquatch brings both everyday content creators and consumers.”