摘要
结合车辆通信中语音信号的特殊性,利用傅里叶变换和最大离散熵定理,对含强噪语音的短时频谱进行分析,构造出一种熵函数来对语音信号进行语音/噪声的判决。以一段语音信号为例进行仿真,研究结果表明,谱熵检测方法计算简单,谱熵值和隔离度较大,具有稳健的抗噪特性,可以应用于车辆通信中语音信号的检测。
Based on the character of vehicle communication and spectral entropy and fast fourier transform, an approach is introduced to voice detection that differs from normal approach via energy, correlation and zero-crossing rate. By measuring the gross shape of the short-term speech spectrum using spectral entropy to detect voice segment and silent segment, it is shown that the spectral entropy can be used effectively even in heavy background noise. A section voice is recorded to simulate. The results show that the approach via spectral entropy has good performance for anti-noise, and it can be applied to vehicle communication.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2005年第5期858-862,共5页
Journal of Central South University:Science and Technology
基金
湖南省教育厅科研基金资助项目(03C499)
关键词
车辆通信
语音检测
谱熵
快速傅里叶变换
vehicle communication
voice detection
spectral entropy
fast Fourier transform
