Figure 14From: Efficient voice activity detection algorithm using long-term spectral flatness measure Total misclassification error as a function of  M and  R combination for machine gun, speech babble, and speech-shaped noises. Upper row: machine gun noise, middle row: speech babble noise, and lower row: speech-shaped noise. SNR= −10, −5, 0, 5, and 10 dB.Back to article page