NICT-ATR Speech-to-Speech Translation System

This paper describes the latest version of speech-to-speech translation systems developed by the team of NICT-ATR for over twenty years. The system is now ready to be deployed for the travel domain. A new noise-suppression technique notably improves speech recognition performance. Corpus-based approaches of recognition, translation, and synthesis enable coverage of a wide variety of topics and portability to other languages.

• Type: Conference
• Year: 2007
• Where: ACL
• Authors: Eiichiro Sumita, Tohru Shimizu, Satoshi Nakamura
• Keywords: ACL 2007, Computational Linguistics, Speech Recognition Performance, Speech-to-speech Translation Systems, Synthesis Enable Coverage