将非线性理论应用到端点检测中,提出一种利用次序统计滤波(OSF)来进行汉语耳语音的端点检测的方法。对信噪比为2-10dB的耳语音的测试样本进行仿真试验,结果表明,该方法能较准确地检测到汉语耳语音的端点。
This paper proposed a method to detect the endpoint of whispered Chinese based on order statistics filter (OSF) which is a kind of nonlinear filters. The results of experiments, which have been performed on 720 whispered speech samples with a 2-10dB SNR, show the efficiency of the proposed whispered speech endpoint detection algorithm.