Guido Drexel

Learn More
This paper describes a morphological component in a speech recognition architecture for German dealing with the recognition of compounds from their individual constituents. The speci cation of our morphological model allows for variation in functionality, e.g. the reconstruction of split compounds, of lexicalised, and of non-lexicalised (unknown) compounds.(More)
This paper describes a morphological component in a speech recognition system for German dealing with the construction of complex word form hypotheses out of a lattice of simplex forms. Our example is the recognition of compounds from their individual components. Evaluation results are presented for speech recognition with and without morphologically based(More)
This paper describes a phonological event parser for spoken language recognition which has been provided with a parametrisable development environment for examining the extent to which linguistically signi cant issues such as linguistic competence (structural constraints) and linguistic performance (robustness) can play a role in the spoken language(More)
  • 1