MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices

Alexandre Patry, Philippe Langlais


Abstract
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.
Anthology ID:
L08-1485
Volume:
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)
Month:
May
Year:
2008
Address:
Marrakech, Morocco
Editors:
Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/293_paper.pdf
DOI:
Bibkey:
Cite (ACL):
Alexandre Patry and Philippe Langlais. 2008. MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).
Cite (Informal):
MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices (Patry & Langlais, LREC 2008)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/293_paper.pdf