Impact of Endpoint Detection on Seaker Recognition
GU Xiuxiu
ZHAO Yuxiao
ZHANG Erhua
Abstract：Since the discovery in speaker recognition research ,the voice signal includes mute segment ,consonants seg-ment and voiced segment in which the main speaker's personality traits inherent .Mute segment and consonant segment in-volved in recognition will significantly reduce the rate of speaker recognition .A number of experiments demonstrate that re-moving of mute segment and consonants segment with endpoint detection has significantly improved the recognition rate .For this situation ,the speech after endpoint detection is pointed out ,whose distribution will be more in line with a Gaussian dis-tribution .The experimental results show that the more accurate endpoint detection ,the recognition result is better .
Keywords：endpoint detectionfeature extractionshort-time emergyshort-time zero-crossing rateMFCCGMM
Publication Date：2014-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 984-987 )