Measurement of the Effects of Temporal clipping on Speech Quality

Abstract

This paper investigates the effects of temporal clipping, which can result from voice activity detection (VAD), or echo canceller's nonlinear processor (NLP), on speech quality. Mean opinion score (MOS) is used as an index of speech quality. A nonintrusive algorithm, based on the clipping locations, is proposed to predict the speech quality. The algorithm shows excellent performance, the correlation coefficient between the prediction and the measurement is about 0.975, and the root mean square error for the prediction is 0.18 MOS