Microsoft demos 'near real-time' language translation for Skype voice calls
Microsoft breaking boundaries
Since the dawn of humanity our propensity to speak in different tongues has limited our ability to fully communicate with everyone we encounter, but Microsoft reckons it might have sorted all that.
At the Code conference on Tuesday, the firm demonstrated 'near real-time' language translation for voice calls for Skype, which works just like having a real interpreter as part of the conversation.
Amazingly, the English-to-German Skype Translator demo from CEO Satya Nadella wasn't just your average proof of concept envisioning the tech of tomorrow either.
A beta app expected to land for Windows 8 users before the end of 2014, with a commercial roll out possible within a couple of years. Microsoft is also working on adding more languages and says the feature may come at a cost for users.
Resolving the mismatch
Microsoft said the project required a number of breakthroughs from its Machine Translation Team and researchers and engineers across the company in speech recognition and translation.
"The interesting thing about this project," project leader Arul Menezes says, "is we've got these two fairly complex technologies coming together for the first time to provide this end-to-end user experience."
The key breakthrough came in 2010 when the team developed a system for real-time speech-to-text and speech-to-speech translation of voice calls.
Get daily insight, inspiration and deals in your inbox
Sign up for breaking news, reviews, opinion, top tech deals, and more.
Since then the firm has been analysing conversational data, the way people speak on social media and the differences between how people write and talk in order to fine tune the technology.
"That's one of the things over the last year that my team's been doing, resolving the mismatch between the way people talk and the way they write," Menezes added on the Microsoft Research blog.
"If your translation system is focused on written text, it works very poorly with spoken language."
The firm says its efforts over the last few years have come close to solving what it had previously considered "an impossible task."
It's certainly an example of how Microsoft, with its vast resources and knowledge can take an established property like Skype and take it to unheard of levels. We're excited to give this a try.
A technology journalist, writer and videographer of many magazines and websites including T3, Gadget Magazine and TechRadar.com. He specializes in applications for smartphones, tablets and handheld devices, with bylines also at The Guardian, WIRED, Trusted Reviews and Wareable. Chris is also the podcast host for The Liverpool Way. As well as tech and football, Chris is a pop-punk fan and enjoys the art of wrasslin'.