Yang Guoqing, Mo Hongqiang, Li Wen, Lian Lianfang, Zheng Zeguang
College of Automation Science and Engineering, South China University of Technology, 510641 Guangzhou, China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2010 Jun;27(3):544-7, 555.
The endpoint detection of cough signal in continuous speech has been researched in order to improve the efficiency and veracity of manual recognition or computer-based automatic recognition. First, using the short time zero crossing ratio(ZCR) for identifying the suspicious coughs and getting the threshold of short time energy based on acoustic characteristics of cough. Then, the short time energy is combined with short time ZCR in order to implement the endpoint detection of cough in continuous speech. To evaluate the effect of the method, first, the virtual number of coughs in each recording was identified by two experienced doctors using the graphical user interface (GUI). Second, the recordings were analyzed by automatic endpoint detection program under Matlab7.0. Finally, the comparison between these two results showed: The error rate of undetected cough is 2.18%, and 98.13% of noise, silence and speech were removed. The way of setting short time energy threshold is robust. The endpoint detection program can remove most speech and noise, thus maintaining a lower rate of error.
为了提高人工识别或基于计算机的自动识别的效率和准确性，人们对连续语音中咳嗽信号的端点检测进行了研究。首先，利用短时过零率（ZCR）来识别可疑咳嗽，并根据咳嗽的声学特征获取短时能量的阈值。然后，将短时能量与短时ZCR相结合，以实现连续语音中咳嗽的端点检测。为了评估该方法的效果，首先，由两名经验丰富的医生使用图形用户界面（GUI）确定每个记录中的虚拟咳嗽次数。其次，在Matlab7.0下通过自动端点检测程序对记录进行分析。最后，这两个结果之间的比较表明：未检测到咳嗽的错误率为2.18%，并且98.13%的噪声、静音和语音被去除。设置短时能量阈值的方法是稳健的。端点检测程序可以去除大部分语音和噪声，从而保持较低的错误率。
