NTT DoCoMo exhibits on-the-fly speech translation, lets both parties just talk (video)

The race to smash linguistic barriers with simultaneous speech-to-speech translation remains wide open, and Japanese mobile operator NTT DoCoMo has just joined Google Translate and DARPA at the track. Whereas Google Translate’s Conversation Mode was a turn-based affair when it was demoed back in January, requiring each party to pause awkwardly between exchanges, NTT DoCoMo’s approach seems a load more natural. It is not according to new technology as such, but brings together a number of existing cloud-based services that recognize your words, translate them after which synthesize new speech within the other language — hopefully all before your cross-cultural buddy gets bored and hangs up. As you will see within the video after the break, this speed comes with the sacrifice of accuracy and it’ll want a lot of labor after it’s trialled later within the year. But hey, combine NTT DoCoMo’s system with a Telenoid robot or kiss transmission device and you’ll always underline your meaning physically.

Source

This post is tagged: Both, DoCoMo, exhibits, Just, Lets, NTT, on the fly, parties, speech, talk, Translation, video