Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2007 | ACL | new noise-suppression technique,wide variety,corpus-based approach,speech recognition performance,nict-atr speech-to-speech translation system,speech-to-speech translation system,latest version,travel domain,twenty year,speech recognition |
Field | DocType | Volume |
Computer science,Speech recognition,Speech to speech translation,Artificial intelligence,Software portability,Natural language processing,Speech recognition performance,Speech technology | Conference | P07-2 |
Citations | PageRank | References |
1 | 0.37 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eiichiro SUMITA | 1 | 1466 | 190.87 |
Tohru Shimizu | 2 | 57 | 12.85 |
Satoshi Nakamura | 3 | 1099 | 194.59 |