NTT Docomo demonstrated a cloud based automatic interpretation service which is currently in development, at Wireless Japan 2011. In this demonstration, docomo staff at the company's research center in Yokosuka read a newspaper article in Japanese, which is then interpreted in real-time and sent to the receiver at the exhibition hall. 

This was achieved by the integration of a range of existing technologies such as voice recognition, machine translation, and voice synthesis.


"We are not using our own company's technology in the integration of voice recognition, machine translation and voice synthesis here, but are rather using what we think is the best technology from around the world. Our own technology here consists of achieving real-time communication of content like "Hello, yes, yes", in other words, making it happen in real time through by combining Internet technologies."

"Voice recognition is not at 100% yet. In order for customers to use it we have to improve recognition accuracy a little more, and we also need to improve translation accuracy a little more as well. However, we really don't know how much time it will take to bring accuracy to 100%. Conversely, we are considering scenarios in which customers who could accept a certain level of inaccuracy could use this. Possibly even at this level of accuracy there are ways to use this so that some customers would be able to appreciate its convenience, so we plan to recruit people to monitor the service and offer it on a trial basis this year."

Japan's largest mobile phone carrier aims to commercialize the system by the second half of fiscal 2012. The free trial service will be offered to corporate clients while soliciting about 400 customer monitors, the firm said.

Tourist facilities such as Universal Studios Japan, retail companies and hospitals will also take part in the test operations, it said. (DigInfo)