Proceedings of the Acoustical Society of Korea Conference (한국음향학회:학술대회논문집)
- spring
- /
- Pages.25-28
- /
- 2002
Reconstruction Effect of the Spectral Entropy for the Voice Activity Detection
음성 활동 구간 검출을 위한 스펙트랄 엔트로피의 재구성 효과
- Kwon HO-Min (Dept. of Electronics, Dong-A University) ;
- Han Hag-Yong (Dept. of Electronics, Dong-A University) ;
- Lee Kwang-Seok (Dept. of Electronic & Information Engineering, Kyung-il University) ;
- Koh Si-Young (Dept. of Electronics, JinJu National University) ;
-
Hur Kang-In
(Dept. of Electronics, Dong-A University)
- Published : 2002.07.01
Abstract
Voice activity detection is important Problem in the speech recognition and communication. This paper introduces feature parameter which is reconstructed by the spectral entropy of information theory for the robust voice activity detection in the noise environment, analyzes and compares it with the energy method of voice activity detection and performance. In experiment, we confirmed that the spectral entropy is more feature parameter than the energy method for the robust voice activity detection in the various noise environment.
Keywords