Wednesday, June 27, 2012

New VoiceTra4U-M App Let's You Communicate With 95% Of The World

Speech Translation in 23 Languages will allow up to 5 users to chat simultaneously. International Research Consortium (U-STAR) with members from 23 Countries unveils a Speech Translation Application, “VoiceTra4U-M”. Singapore’s Institute for Infocomm Research (I2R), an institute of the Agency for Science, Technology and Research (A*STAR), was a founding member of U-STAR.

An international research collaboration entity, "Universal Speech Translation Advanced Research Consortium (U-STAR)" consisting of 26 institutes from 23 countries, with an aim to enable everyone in the world to communicate without any language barriers, has developed a speech translation application called “VoiceTra4U-M”, allowing 5 people to chat simultaneously in 23 different languages (as of June 2012).

“VoiceTra4U-M” can be downloaded for free from the App Store. It allows up to 5 users to chat in different languages from their own devices, in real-time either face-to-face or remotely from all around the world.


1. The rapid growth of information communication technologies and transportation has resulted in accelerating the explosive increase of interactions between people across the globe today. However, language barriers still stand tall and interfere with people’s communication. As a useful means to break these barriers, speech-to-speech translation systems; which allow a user’s speech to be translated into a selected language with a synthesized voice, is now drawing attention from various fields. Ongoing research in institutes all over the world has been taking place for speech recognition, machine translation, and acoustic synthesis. Connecting these speech translation servers in respective countries via a network became a pre-requisite in order to realize simultaneous multilingual speech translation. This was when the Consortium of U-STAR1, Universal Speech Translation Advanced Research, was established.

2. Such a framework in the network-based speech-to-speech translation system brings huge advantages, as organizations need simply connect their speech translation servers to the U-STAR server, whenever they need to translate their own languages into multiple languages, and has accelerated further development and research in the speech translation field.

New Achievement

3. U-STAR, currently comprised of 26 institutes from 23 countries, has been conducting ongoing research on speech translation. U-STAR and its members have collaboratively developed the multilingual speech translation system to provide translation services via publicly-released client application, by connecting the servers of U-STAR member institutes mutually, with the communication protocol which was implemented based on the ITU-T recommendations F.745 and H.625. U-STAR hope to see people use “VoiceTra4U-M” in various occasions when translation and interpretation are requested at global events, such as the London Olympic Games in July 2012, and that “VoiceTra4U-M” may come in handy for people wishing to overcome language barriers. For more details on how to use the application, please refer to the appendix.

Experiment Period : From end of June 2012 - March 31st, 2013 (Estimated), Including the London Olympics Period

Experiment Area :  All Areas Around the World where iPhones are available

Future Plans 
4. More languages will be available when other research entities participate by plugging in the U-STAR speech translation communication protocol libraries. U-STAR also seeks to utilize the log data of speech translation collected from field experiments, helping each research organization raise their accuracies in speech translation technology, as well as encouraging business opportunities for the speech translation service to be cultivated in various markets.

*iPhone is a trademark of Apple Inc. App Store is a trademark of Apple inc., registered in the U.S. and other countries

U-STAR: The Universal Speech Translation Advanced Research Consortium

Objectives of U-STAR
As it is not an easy task for a single research institute to develop a multilingual speech translation system, "U-STAR" which consists of member institutes worldwide will collaboratively challenge to realize a network-based speech translation system as shown in Diagram 1.

Network-based Speech Translation System Configuration
Each institute respectively builds and operates servers for speech recognition, machine translation, and acoustic synthesis.

Users will select a set of languages to be translated within the iPhone application.
According to what the users have selected, the control server (operated by NICT) connects to S2ST servers (operated respectively by each institute)

Communication protocols and interfaces are implemented based on the ITU-T recommendations F.745 and H.625.

Establishment and Transition
A research collaboration group, known as the Asian Speech Translation Advanced Research Consortium (A-STAR), first started out in the Asian regions in 2006. In 2009, A-STAR successfully developed the world's first network-based S2ST system enabling 8 different languages in Asia to be translated over the network.

In 2010, A-STAR shifted to U-STAR, transforming not only its name but to a worldwide consortium with the aim of establishing a more global system and expanding its network.

U-STAR and its Members
26 Institutes in 23 Countries (as of June, 2012)

*The orange areas indicate the countries that use the language U-STAR has covered so far, as their official language.


Agency for the Assessment and Application of Technology (BPPT), Indonesia
Institute of Automation, Chinese Academy of Sciences (CASIA), China
Center for Development of Advanced Computing (CDAC), India
Electronics and Telecommunications Research Institute (ETRI), Korea
Institute for Infocomm Research (I2R), Singapore
Institute of Information Technology (IOIT), Vietnam
National Electronics and Computer Technology Center (NECTEC), Thailand
National Institute of Information and Communications Technology (NICT), Japan
Department of Information Technology and Telecom (DITT), Bhutan
Al-Khawarizmi Institute of Computer Science, UET (KICS-UET), Pakistan
Language Technology Kendra (LTK), Nepal
Mongolian University of Science and Technology (MUST), Mongoli
National University of Mongolia (NUM), Mongolia
University of Colombo School of Computing (UCSC), Sri Lanka
University of the Philippines Diliman (UPD), Philippines
Budapest University of Technology and Economics Dept. of Telecommunications and Media Informatics (BME-TMIT), Hungary
National Center of Scientific Research (CNRS-LIMSI), France
Institute of Systems and Computer Engineering - Research and Development in Lisbon, (INESC-ID), Portugal
Polish-Japanese Institute of Information Technology, (PJIIT), Poland
Pázmány Péter Catholic University, (PPKE), Hungary
University of Sheffield, Department of Computer Science, Speech and Hearing Group, (SpandH), UK
KU Leuven,Dept. Electrical Engineering, division PSI-Speech, (ESAT), Belgium
Technische Universität München, (TUM), Germany
Trinity College Dublin, (TCD), Ireland
Center of Research for Advanced Technologies of Informatics and Information Security, (TUBITAK), Turkey
Ulm University - Institute of Communications Engineering, (UUlm) Germany

ITU-T Standardization

The "Multilingual Speech Translation System and its Service" in which U-STAR has developed, uses network-based speech-to-speech translation protocols, internationally standardized by NICT (Based on Recommendations of F.745, and H.625).

International Telecommunication Union Telecommunication Standardization Sector:

ITU-T Recommendation F.745
Functional requirements for automatic speech recognition, machine translation, and network-based speech to speech translation services

Recommendation ITU-T H.625 defines the system architecture for network-based speech-to-speech translation (S2ST) on the basis of Recommendation ITU-T F.745 and serves as a technical introduction to the subsequent definitions of detailed system components and protocols.

 How to Use Multilingual and Multi-party (up to 5) Conversation Application, “VoiceTra4U-M”

List of Languages Available for Input /Output


Voice Input:
Voice Output:

Text Input:
Text Output:
17 Languages
14 Languages

23 Languages
23 Languages

How to Use the “VoiceTra4U-M” Application

About Institute for Infocomm Research (I2R)
The Institute for Infocomm Research (I²R pronounced as i-squared-r) is a member of the Agency for Science, Technology and Research (A*STAR) family. Established in 2002, our mission is to be the globally preferred source of innovations in `Interactive Secured Information, Content and Services Anytime Anywhere’ through research by passionate people dedicated to Singapore’s economic success. I²R performs R&D in information, communications and media (ICM) technologies to develop holistic solutions across the ICM value chain. Our research capabilities are in information technology, wireless and optical communication networks, interactive and digital media, signal processing and computing. We seek to be the infocomm and media value creator that keeps Singapore ahead. For more information about I2R, please

About the Agency for Science, Technology and Research (A*STAR)
The Agency for Science, Technology and Research (A*STAR) is the lead agency for fostering world-class scientific research and talent for a vibrant knowledge-based and innovation-driven Singapore. A*STAR oversees 14 biomedical sciences and physical sciences and engineering research institutes, and six consortia & centres, located in Biopolis and Fusionopolis as well as their immediate vicinity. A*STAR supports Singapore's key economic clusters by providing intellectual, human and industrial capital to its partners in industry. It also supports extramural research in the universities, and with other local and international partners. For more information about A*STAR, please



  1. VoiceTra4U-M helps multiple users (up to 5) communicate in different languages. From ccie lab

  2. Windows phone 8 will have real multitasking technology, is this true? From cisco ccie