Summary of the paper

Title MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices
Authors Alexandre Patry and 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.
Language Language-independent
Topics Machine Translation, SpeechToSpeech Translation, Tools, systems, applications, Multilinguality
Full paper MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices
Slides -
Bibtex @InProceedings{PATRY08.293,
  author = {Alexandre Patry and Philippe Langlais},
  title = {MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices},
  booktitle = {Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)},
  year = {2008},
  month = {may},
  date = {28-30},
  address = {Marrakech, Morocco},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-4-0},
  note = {http://www.lrec-conf.org/proceedings/lrec2008/},
  language = {english}
  }

Powered by ELDA © 2008 ELDA/ELRA