The Effect of Explainability on Trust
in Neural Audio Processing Systems

What is this study about?

You will listen to short audio clips processed by different AI compression systems, then answer questions about how much you trust each system. The whole study takes about 15–20 minutes.

How it works — 4 sessions
1
Pick an audio clip Choose a famous recording or upload your own file.
2
The system compresses it An AI shrinks the audio to a tiny fraction of its original size, then rebuilds it. Some systems will explain what they did; others won't.
3
Listen & compare Play the original and processed clips side-by-side to hear the difference.
4
Rate trust & quality Answer 12 short questions about how much you trust the system, then give the audio a quality rating. Repeat for 4 different systems.
Informed Consent

Your participation is entirely voluntary. All data are collected anonymously; no personally identifiable information is stored. You may withdraw at any time by closing your browser. The anonymised data will be used solely for academic research purposes.

Audio recordings: if you choose to upload your own audio, it is used solely to demonstrate the compression system during your session. It is deleted from the server immediately after processing and is not stored, retained, or accessible beyond that point. The provided sample recordings are pre-processed and contain no personal data.