Sciweavers

Share
LREC
2008

MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices

10 years 28 days ago
MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices
This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a written text as input, MISTRAL translates word lattices produced by automatic speech recognition systems. The lattices are translated in two passes using a phrase-based model. Our experiments reveal an improvement in BLEU when translating lattices instead of sentences returned by a speech recognition system.
Alexandre Patry, Philippe Langlais
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where LREC
Authors Alexandre Patry, Philippe Langlais
Comments (0)
books