International Symposium on Chinese Spoken Language Processing
August 23-24, 2002
Prosodic Phrase Detection for Chinese TTS using CART and Statistical Model
Minghui Dong, Kim-Teng Lua
School of Computing,
National University of Singapore, Singapore
Determination of prosodic phrase break from text is
one of the important problems in generating good
prosody for Chinese text-to-speech system. In this
paper, we propose a statistical approach for detecting
prosodic phrase breaks. Part-of-speech sequence
information is used as the primary information. The
history of the previous breaks is considered as
constraint in this work. The probabilities are calculated
using CART approach. During the prediction process,
the breaks are dynamically determined. Viterbi
algorithm is applied to find the best break sequence.
We achieved a result of recall of about 89% and
precision of about 85 % for our testing data.
Dong, Minghui / Lua, Kim-Teng (2002):
"Prosodic phrase detection for Chinese TTS using CART and statistical model",
In ISCSLP 2002, paper 99.