MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices

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… (More)

7 Figures and Tables

Topics

  • Presentations referencing similar topics