This paper proposes a method that synthesizes a huge number of words
by concatenating syllabic waveforms
obtained from recorded words selected carefully.
This method assumes that
just the mora position and the mora length represent
enough of the prosodic features
to realize synthesis at the word level.
An experiment study to synthesize Japanese city and town names
with five moras by the proposed method was carried out.
Competitive opinion scores were obtained
by the synthesized voices compared with those obtained by actual voices.
By our estimation, only 17,000 names need to be recorded
to cover the remaining names with 3, 4, and 5 mora,
which totals about 105,000.
word synthesis, slot filling method, syllable,
prosodic features, mora position, mora length