results not only limit the usability of speech transcript, but
also affect the efficiency of the further indexing process. In
our research, we intended to continuously improve the ASR
result for German lectures by building new speech training
data based on the open-source ASR tool. However, in the
open-source context, it lacks method for generating the German
phonetic dictionary automatically, which is the one of
the most important part of an ASR software. Therefore, we
developed an automated procedure in order to fill this gap.