|
KMID : 0917520010080010077
|
|
Journal of Speech Sciences
2001 Volume.8 No. 1 p.77 ~ p.91
|
|
|
Analysis of the Timing of Spoken Using a Classification and Regression Tree (CART) Model
|
|
Chung, Hyun Song
Huckvale, Mark
|
|
|
Abstract
|
|
|
|
This paper investigates the timing of Korean spoken in a news-reading speech style in order to improve the naturalness of duratiens used in Korean speech synthesis. Each segment in a corpus of 671 read sentences was annotated with 69 segmental and prosodic features so that the measured duration could be correlated with the context in which it occurred. A CART model based on the features showed a correlation coefficient of 0 79 with an RM E (root mean squared prediction error) of 23 ms between actual and predicted duratiens in reserved test data. These results are comparable with recent published results in Korean and similar to results found in ether languages. An analysis of the classification tree shows that, phrasal structure has the greatest effect on the segment duration, followed by syllable structure and the manner features of surrounding segments. The place features of surrounding segments only have small effects. The model has application in Korean speech synthesis systems.
|
|
|
KEYWORD
|
|
|
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|