About
430 million people worldwide require rehabilitation to address hearing loss (World Health Organization). Yet even in developed countries, only 40% of people who could benefit from hearing aids have them and use them often enough. People believe that hearing aids perform poorly, with the difficulties of hearing speech-in-noise being a key issue.
Speech intelligibility prediction is an active area of research which allows developers and researchers to work on speech enhancement algorithms without relying on slow and expensive human listening tests at every stage of development. The Clarity Prediction Challenges (CPC) aim to encourage the development of new prediction systems which can improve on existing methods.
The Challenge
To allow the development of better hearing aids, we need ways to evaluate the speech intelligibility of audio signals automatically. We need a prediction model that takes the audio produced by a hearing aid and the listener's characteristics (e.g. audiogram) and estimates the speech intelligibility score that the listener would achieve in a listening test.
For the prediction challenge we will provide the following data:- Audio produced by a variety of (simulated) hearing aids for speech-in-noise
- The corresponding clean reference signals (the original speech)
- Characteristics of the listeners (pure tone audiogram, etc.)
- The measured speech intelligibility scores from listening tests, where the listener was asked to say what they heard for the speech-in-noise.
Sign up to the Clarity Challenges Google group to receive updates on this challenge.