论文部分内容阅读
CVR是黑匣子的重要组成部分,通常通过CVR信息来分析飞机故障或导致飞行事故的原因,因为CVR记录了飞机整个飞行过程中几乎所有的座舱声音,包括飞行员间及机组人员间的对话、飞机与塔台之间的通讯,发动机的振动声、开关按钮声以及其他一些背景声。这些声音为还原现场环境提供了一个客观有效的声音证据。因此,舱音识别很有实际操作意义。舱音识别方法有很多的,文献中分析了声音特征包括声音的短时过零率、短时能量以及线性谱等的优缺点,然
The CVR is an important part of the black box. CVR information is often used to analyze the cause of an aircraft malfunction or flight accident because the CVR records almost all cockpit sounds throughout the flight, including pilot-crew conversations, Communication between towers, engine vibration, switch button sounds, and other background sounds. These sounds provide an objective and valid sound proof of the restoration of the scene. Therefore, the vocals recognition is very practical significance. There are many methods of speech recognition. The literature analyzes the advantages and disadvantages of the sound features, including short-time zero-crossing rate, short-time energy and linear spectrum,