Mismatch interpretation by semantics-driven alignment

Martin Huber, Jeremy Jancsary, Johannes Matiasek, and Harald Trost
8th Conference on Natural Language Processing (KONVENS)
October 2006, Konstanz, Germany

This paper describes a method for the alignment of automatically recognized speech transcripts with formatted documents manually derived from the speech recognition results. Novel features of our alignment method are a parametrizable scoring function, an intelligent tokenization system drawing on domain knowledge, and semantic comparisons. The field of application are dictated medical reports processed by automatic speech recognition. 



Please cite as:

title = {Mismatch interpretation by semantics-driven alignment},
author = {Martin Huber and Jeremy Jancsary and Johannes Matiasek and Harald Trost},
booktitle = {8th Conference on Natural Language Processing (KONVENS)},
year = {2006}