Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk in the Stereophonic Case

Speech quality, as evaluated by humans, is most accurately assessed by subjective human ratings. The objective acoustic echo cancellation mean opinion score (AECMOS) metric was recently introduced and achieved high accuracy in predicting human perception during double-talk. Residual-echo suppression (RES) systems, however, employ the signal-to-distortion ratio (SDR) metric to quantify speech-quality in double-talk. In this study, we focus on stereophonic acoustic echo cancellation, and show that the stereo SDR (SSDR) poorly correlates with subjective human ratings according to the AECMOS, since the SSDR is influenced by both distortion of desired speech and presence of residual-echo. We introduce a pair of objective metrics that distinctly assess the stereo desired-speech maintained level (SDSML) and stereo residual-echo suppression level (SRESL) during double-talk. By employing a tunable RES system based on deep learning and using 100 hours of real and simulated recordings, the SDSML and SRESL metrics show high correlation with the AECMOS across various setups. We also investigate into how the design parameter governs the SDSML-SRESL tradeoff, and harness this relation to allow optimal performance for frequently-changing user demands in practical cases.