Long-Term Multi-Band Frequency-Domain Mean-Crossing Rate (FDMCR) Feature

In order to discriminate and mark audio signal segments which include normal human speech and discriminate segments which do not include speech (like silence, music and noise), Speech/Music Discrimination (SMD) systems are used. Using this definition, SMD systems can be considered as a specific or accurate type of speech activity detection system. Here, a new, effective and robust feature in SMD systems is introduced as “Long-Term Multi-Band Frequency-Domain Mean-Crossing Rate (FDMCR)” where high accuracy, low error and further discrimination can be mentioned as its advantages.