基于卷积和门控注意的两阶段视听语音增强算法

王盼蓉,贾海蓉,段淑斐

Two-stage audio-visual speech enhancement algorithm based on convolution and gated attention

Panrong WANG,Hairong JIA,Shufei DUAN

表 6 风雨噪声下不同模块对增强语音PESQ和SNR的影响

Tab.6 Influence of different modules on enhancing speech PESQ and SNR under wind and rain noise

模型 PESQ SNR/dB −10 dB −5 dB 0 dB 5 dB 10 dB −10 dB −5 dB 0 dB 5 dB 10 dB 实验1 2.53 2.59 2.75 2.82 2.88 6.47 6.58 6.83 6.89 6.78 实验2 2.56 2.63 2.78 2.93 2.98 10.52 11.73 12.33 13.33 13.80 实验3 2.70 2.75 2.97 3.13 3.22 11.84 12.95 14.03 14.64 14.68 实验4 2.77 2.79 3.01 3.16 3.25 12.29 13.09 14.11 14.54 14.55