Vibroarthrographic (VAG) signals are sounds or vibrations caused when a knee joint is flexed or stretched. VAG signal collection is noninvasive and can be performed using an accelerometer or microphone attached to the skin. However, the sensor attached to the skin will move with the soft tissue caused by flexion and extension, causing the baseline of the VAG signal to drift. We call these interferences soft tissue movement artifacts (STMAs). In this study, an algorithm is proposed to filter out STMAs. We compare the proposed method's results with noises collected by an accelerometer. The noise reduction effect is evaluated, revealing an 11.85% increase in the peak signal-to-noise ratio and a 28.18% increase in signal-to-noise ratio compared with the case in which STMA noise was not removed.Clinical Relevance-This study focuses on a proposed post-processing method that can remove soft tissue movement artifacts that cause baseline wander and could thus improve the accuracy of clinical applications of VAG signals.