Abstract: Audio mixing is indispensable to achieve the sense of reality in video conference systems. In this paper, a digital audio mixing algorithm with equal-loudness is proposed. Voice activity detection(VAD) is first performed by the average power and short-term autocorrelation sequence of signal. Then, the noise caused by audio mixing directly is filtered by the time-varying filter, where the passband variation of the filter depends on the result of voice activity detection. Finally, to achieve the effect of equal-loudness, the weight of each channel signal in audio mixing is calculated with the average loudness of voice. Simulation results show that the proposed algorithm can make the average loudness of each channel signal close to the same, which can effectively decrease the distortion of small-signal.