Toshiba has developed a cell phone translation system for English, Chinese and Japanese. The app entails voice recognition, a trilingual translation system and synthesis. The software was demonstrated on Toshiba’s TG01 and supports voice recognition, synthesis for output and two translation methods – statistical machine translation for English-Chinese, Chinese-English-Japanese and rule-based translation for the remaining ones.
In use the software first employs speech recognition to determine the language and what has been said. It then uses one of two translation methods — statistical machine translation or rule-based machine translation — to parse the sentence and break it down into its components. The translation is then performed and a speech synthesis engine outputs the result. Toshiba’s research department claims its almost done and can be sold soon.
