Ever wonder what you’d sound like speaking German? Or maybe Mandarin? Microsoft Research has a new technology they’re cooking up which will take the sound of your voice and synthesise it as part a spoken language translator.
According to MIT’s Technology Review, the system in it’s current form requires an hour of training (which, presumably, means an hour of you talking to a computer), and can translate between 26 different languages.
That model is converted into one able to read out text in another language by comparing it with a stock text-to-speech model for the target language. Individual sounds used by the first model to build up words using a person’s voice in his or her own language are carefully tweaked to give the new text-to-speech model a full ability to sound out phrases in the second language.
As you can tell from Tech Review’s audio clips, the voice still sounds a bit robotic but still very much of the speaker (who happens to be Rick Rashid from Microsoft Research). Microsoft says that the immediate applications for this tech are language education and foreign travel, and believe that the users will find hearing their own voice to be assuring. Personally, I might be a bit creeped out, but that’s just me! [Technology Review]
Image: IR Stone/Shutterstock