An End-to-End Listening Test Platform

Subjective listening tests are routinely conducted by academic researchers and industry professionals to assess the quality of various speech and audio processing algorithms. Some examples include low bit rate audio encoding, background noise reduction, text to speech synthesis or any type of audio enhancement or transformation one might think of. Listening tests often take place in controlled environments for the sake of consistency, but in many cases, listening tests could be undertaken remotely using a suitable web interface. The requirement for a web-based listening test platform has become more apparent in light of the recent implications of COVID-19. Despite the work of several projects in the past, there is no fully hosted listening test platform which allows for easy test creation, deployment and data collection. In this demonstration paper we present a fully functional end-to-end listening test platform which allows a user to create and share MUSHRA, ACR and A/B tests within minutes. Collected data can then be downloaded in CSV form.