Crowdsourcing approach for subjective evaluation of echo impairment
This provides a cost-effective and scalable method for subjective evaluation of echo impairment in real-time communication systems, addressing a bottleneck in AEC assessment.
The paper tackled the problem of evaluating acoustic echo cancellers by showing that objective metrics poorly correlate with subjective measures, and introduced an open-source crowdsourcing tool for subjective evaluation, which was validated as accurate and reproducible and used in the ICASSP 2021 AEC Challenge.
The quality of acoustic echo cancellers (AECs) in real-time communication systems is typically evaluated using objective metrics like ERLE and PESQ, and less commonly with lab-based subjective tests like ITU-T Rec. P.831. We will show that these objective measures are not well correlated to subjective measures. We then introduce an open-source crowdsourcing approach for subjective evaluation of echo impairment which can be used to evaluate the performance of AECs. We provide a study that shows this tool is accurate and highly reproducible. This new tool has been recently used in the ICASSP 2021 AEC Challenge which made the challenge possible to do quickly and cost effectively.