Gang Ju You, Ok Keun Shin

The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 7, No. 7, pp. 2246-2253, Jul. 2000
10.3745/KIPSTE.2000.7.7.2246,   PDF Download:

Abstract

In this paper, we show that one can enhance the performance of blind segmentation of phoneme boundaries by adopting the knowledge of Korean syllabic structure and the regions of voiced/unvoiced sounds. The proposed method consists of three processes the process to extract candidate phoneme boundaries, the process to detect boundaries of voiced/unvoiced sounds, and the process to select final phoneme boundaries. The candidate phoneme boundaries are extracted by clustering method based on similarity between two adjacent clusters. The employed similarity measure in this process is the ratio of the probability density of adjacent clusters. To detect the boundaries of voiced/unvoiced sounds, we first compute the power density spectrum of speech signal in 0~?400Hz frequency band. Then the points where this power density spectrum variation is greater than the threshold are chosen as the boundaries of voiced/unvoiced sounds. The final phoneme boundaries consist of all the candidate phoneme boundaries in voiced region and limited number of candidate phoneme boundaries in unvoiced region. The experimental result showed about 40% decrease of insertion rate compared to the blind segmentation method we adopted.

Statistics
Cite this article