Microsoft Research: Voice Translate

I I don’t know about you, but I find polyglots (people with a high degree of proficiency in several languages) to be the most fascinating of people around; the thought of being able to communicate in a language with an entirely different character set like Russian, or a completely different accent set where there is no alphabet like Mandarin or Cantonese Chinese is amazing. Tools like Google Translate, apps for smartphones, and even (to an extent) software like Rosetta Stone get some people part of the way there, but it’s only until you’re put into the situation of having to use the skills you’ve learned that you realise you may not know as much as you thought you had. This brings me to something that I find strikingly useful and could possibly give Google a run for their money with their Google Translate; a project that Microsoft are developing within their Research department.

The tool is named Monolingual TTS and it allows you to speak in your own native language, and have it outputted via a voice that (is somewhat synthesised by a computer to) sound(s) a lot like your own. The videos posted by Microsoft Research demonstrate a man speaking in English, and result in him having his speech translated entirely into Mandarin Chinese. Not only does this demonstrate the amazing geekery of the Chinese researchers in Beijing, and how far we’ve come in technology,but in some ways it could also help to demonstrate how lazy we’re becoming with the Internet.

Nevertheless, this does show what amazing things can be done when people put their heads together, and kudos to those people with those great minds if they are able to achieve this kind of tool. At present it is claimed to have the ability to translate to some of the worlds most popular and most widely spoken languages (Chinese, French, Spanish, and of course English).

The principle researcher in Microsofts Speech group explains how they have intentions to do“..quite a few scenario applications”, and how he intends to be able “..to sit in my office, send my avatar to meet somebody in Beijing, and I can speak in English and the avatar speaks in Mandarin in real-time”. It truly is a substantial step to be able to come this far in communication, and my thoughts are that if done properly this could become one of the most well trusted and used tools on the Internet. I could argue that this may gain even more traction than Google Translate if the ability to have simultaneous conversations is feasible, of course, the only problem when in another country is the massive phone bill you’d accumulate from roaming charges – on second thoughts, maybe I’ll stick to a phrase book!