|
KMID : 0917520020090040253
|
|
Journal of Speech Sciences
2002 Volume.9 No. 4 p.253 ~ p.263
|
|
|
The Study for Advancing the Performance of Speaker Verification Using Individual Voice Information
|
|
|
|
|
Abstract
|
|
|
|
In this paper, we propose new algorithm of speaker recognition which identfies the speaker using the information obtained by the intensive speech feature analysis such as pitch, intensity, duration, and formant, which are crucial parameters of individual voice, for candidates of high percentage of wrong recognition in the existing speaker recognition algorithm. For testing the power of discrimination of individual parameter, DTW (Dynamic Time Warping) is used. We newly set the range of threshold which affects the power of discrimination in speech verification such that the candiates in the new range of threshold are finally discriminated in the nest stage of sound parameter analysis. In the speaker verification test by using voice DB which consists of secret words of 25 males and 25 females of 8 ㎑ 16 bit, the algorithm we propose shows about 1% of performance improvement to the existing algorithm.
|
|
|
KEYWORD
|
|
|
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|
|