The use of duration similarity templates in speech rhythm training

We present a novel method of speech rhythm training for a mora-timed language. Previous works were mainly concerned with a case-by-case training. In this work we devise "duration templates" describing a set of words with similar speech rhythm and then apply them to training speech rhythms of learners. Especially, in this system each mora is measured by the ratio of its duration to the whole duration of a word, not by absolute millisecond measurement.