Acquisition of in-domain training data to build speech recog-
nition systems for under-resourced languages can be a costly,
time-demanding and tedious process. In this work, we pro-
pose the use of machine translation to translate English tran-
scripts of telephone speech into Czech language in order to
improve a Czech CTS speech recognition system. The trans-
lated transcripts are used as additional language model train-
ing data in a scenario where the baseline language model is
trained on off- and close-domain data only. We report per-
plexities, OOV and word error rates and examine different
data sets and translators on their suitability for the described
task.