U-Star is a spinoff from the Singapore government A*Star research institute. U-Star has a translation application. The Universal Speech Translation Advanced Research Consortium is an international research consortium conducting research and development on a network-based speech-to-speech translation (S2ST) system, with the aim of breaking the language barriers of the world. U-STAR are implemented with ITU-T standardization protocols, F.745 and H.625.
This application is the multi-device application “VoiceTra4U-M.” It helps multiple users (up to 5) communicate in different languages, in real time either face to face or remotely.
The application contributes to breaking the barriers of modalities other than language as well. For instance, it helps users to communicate with the visually-impaired via spoken word, or with the hearing-impaired via text input.
This application mainly targets the field of travel-related conversations in airports, hotels, shops, or restaurants. The application covers 31 languages. (See below for the list of the Languages)
U-STAR has also initially focused on translating words and phrase related to tourism, making it 80 to 90 per cent accurate versus Google’s 40 to 60 per cent accuracy – though of course, this accuracy falls if you want to discuss a topic not covered by the app.
The app will soon be available for free from the App Store and U-STAR hopes that tourists visiting the UK will use it during the Olympics, allowing the researchers to gather experimental data and improve the service.
The application can be used for iPad2, iPod touch (4G), and the succeeding models.
As the number of computers for this experiment is limited, we would like to restrict the chat time to one hour so that we’re able to offer our service to as many users as possible.
Q: Some translations are wrong.
A: We developed this application with the aim of performing translation for the travel domain, as follows:
“How much does it cost to go to Kyoto station by taxi?”
“Can I get a little discount?”
“Where is the restroom?”
It cannot translate incomprehensible utterances, exclusive words, or sentences outside the travel domain into travel conversation.