Listening Tests
I started making a series of listening tests. These might eventually help us figure out e.g. the minimum acceptable audio sample-rate, what words people would use to search for sounds, or more generally if people find certain synthesis algorithms to be better than others, or as good as real recordings. They contain placeholder audio files right now. But I'm putting them here a) for feedback, and b) to facilitate focusing the discussion surrounding project outcomes.
The code for the listening tests has its own repository: https://github.com/michaelkrzyzaniak/Listening_Tests/tree/master
Classification
Take this test hereFigure 1: Screenshots of the classification test and its results.
Discrimination
Take this test hereFigure 2: Screenshots of the discrimination test and its results.
Ranking
Take this test hereFigure 3: Screenshots of the ranking test.
Word Cloud
Take this test hereFigure 4: Screenshots of the word cloud test and its results.
Video Coherence
Take this test hereFigure 5: Screenshot of the video coherence test.
This comment has been removed by the author.
ReplyDeleteMichael, this is very interesting.
ReplyDeleteA lot of our people are on holiday at the moment but I will get some of the sound designers to try out these tests as soon as we can.
Keep up the good work.
Many thanks
Thanks! No rush on having sound designers look at this; it actually isn't ready yet. I just put in fake sound files so I could design the interface, so let's wait until we have more synthesized sounds that we are happy with.
DeleteMike, thanks for that and please let us know when you are happy for this to be tested?
DeleteThese mock ups are very helpful for knocking up a quick experiment once you have some test files. Although simple, I believe we can get meaningful insights with even a small number of tests. For me, the ranking one seems likely to be most useful for evaluating engineering refinements, where the others can provide validation, benchmarking and summarisation.
ReplyDelete