Institute for Infocomm Research Successfully Completes Its First Asian Network-Based Speech-to-Speech Translation System

Singapore, Singapore, July 31, 2009 --(PR.com)-- Ever wished for technology that can translate your own conversation as you speak to eight different Asian friends in their native languages? A*STAR’s Institute for Infocomm Research (I2R), who is a member of the Asian Speech Translation Advanced Research Consortium, has invented a technology that can do just that. It operates with the help of a portable device and does a real-time network-based speech translation as you speak.

The Speech Translation team in I2R, led by Dr Li Haizhou developed this technology over a span of two years that enables speech translation between Malay language and any of the eight other Asian languages - Japanese, Chinese, Korean, Thai, Indonesian, Vietnamese, Hindi and English.

The Asian Speech Translation Advanced Research Consortium was founded to create a basic infrastructure for spoken language communication to overcome the language barriers in the Asia-Pacific region.

It will launch “the first Asian network-based speech-to-speech translation system” that can perform real-time, location-free, multi-party communication between speakers of different Asian languages today. Originally started by six members, the Asian Speech Translation Advanced Research Consortium was established in June 2006 by the National Institute of Information and Communications Technology (NICT) and the Advanced Telecommunications Research Laboratories (ATR).

Founding countries included Japan (NICT/ATR), Korea (Electronics and Telecommunications Research Institute - ETRI), Thailand (National Electronics and Computer Technology Center - NECTEC), Indonesia (Badan Pengkajian Dan Penerapan Teknologi or The Agency For the Assessment and Application Technology - BPPT), China (National Laboratory of Pattern Recognition of the Institute of Automation of Chinese Academy of Sciences - NLPR-CASIA), and India (Centre for Development of Advance Computing – C-DAC). In 2008, Vietnam (Institute Of Information Technology - IOIT) and Singapore, represented by I2R, joined the Consortium.

The consortium is working collaboratively to collect Asian language corpora[1], to create common speech recognition and translation dictionaries, to develop Web service speech translation modules for Asian languages, and to standardize interfaces and data formats for connecting speech translation modules internationally.

Professor Lye Kin Mun, Deputy Executive Director (Research) said, “I2R has come a long way in developing speech recognition and machine translation technologies. Today’s demonstration demonstrates our technological capabilities working with other Asian partners in breaking down communication barriers. We hope to work with more countries on a global scale with this imminent success.”

The I2R team is led by Dr. Li Haizhou, Department Head of Human Language Technology, with members, Dr. Ma Bin, Ms. Aw Ai Ti, Dr. Vladimir Pervouchine, Ms. Tong Rong, Mr. Bai Shuanhu, and Ms. Sharifah Mahani Aljunied.

###

[1] Collection of recorded remarks used for linguistic analysis