【摘要】 研究连续语音流中咳嗽信号的端点检测,在保持低漏检率的前提下,尽可能排除语音等干扰信号,以提高后续人工判断的效率或机器识别的准确率。从咳嗽的声学特点出发,提出利用过零率来定位可疑咳嗽,从而确定能量阈值的方法。在此基础上,将短时能量和过零率用于连续语音流中咳嗽信号的端点检测。医生识别录音文件中的咳嗽,并标出咳嗽起止点;使用Matlab7.0实现端点检测算法,并将结果与医生人工判断结果相比较,得到咳嗽漏检率为2.18%,同时,排除连续语音流中98.13%的静音或干扰信号。阈值设置方法具有较强的自适应性,并且端点检测能得到咳嗽低漏检率,同时排除大量的静音或干扰信号。更多还原

【Abstract】 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.更多还原