A survey published last week suggested 97% of respondents could not spot an AI-generated song. But there are some telltale signs - if you know where to look.
Here’s a quick guide …
-
No live performances or social media presence
-
‘A mashup of rock hits in a blender’
A song with a formulaic feel - sweet but without much substance or emotional weight - can be a sign of AI, says the musician and technology speaker, as well as vocals that feel breathless.
- ‘AI hasn’t felt heartbreak yet’
“AI hasn’t felt heartbreak yet… It knows patterns,” he explains. “What makes music human is not just sound but the stories behind it.”
- Steps toward transparency
In January, the streaming platform Deezer launched an AI detection tool, followed this summer by a system which tags AI-generated music.
Bullshit. This only applies to fully prompt generated AI music. Tracks that heavily rely on AI based tech as a part of the process are harder to catch, and tracks that only use AI for mixing and mastering are impossible to detect.
I made a track but used AI to autotune and morph my voice to that of a woman’s. It even allowed me to tweak the expressiveness of the voice. The track is 95% human made but the vocals are AI modified. I’m willing to bet that the ration of AI use in a lot of pop music and EDM is a lot higher.
PS: I make music for myself, as a hobby. I just wanted to make something to share with my friends. If you want real music, try bands like Wet Leg, IDLES, GEESE, etc who lean into making low tech music.
EDIT: Thia is an example of a song that is fully generated by AI. All that was fed to the prompt were the lyrics. The AI did everything else itself, including picking the genre. I shared it with a few people to see who’d figure out it was AI slop.
https://youtu.be/oOJ0En2u5DQ
Compression throws me off.
That AI ‘hiss’ is ringing it my ears, but its very, very similar to YT uploads that have been re-encoded like 10 times. Which is a lot of them.
Out of curiosity, I made spectrograms of the AI song and concert that sounds ‘clean’ yet kinda noisy/compressed to me. I won’t tell you which one is which:
Source song, if you are curious: https://www.youtube.com/watch?v=MydFq0io-tQ
That song was a mistake that got generated when I pasted the wrong clipboard into Suno’s Lyrics window on my phone and accidentally submitted it. It has not been processed at all. Suno has a “Remaster” feature that when you are happy with the generated song you can give it a few automated “mix and mastering” passes to generate a cleaner and more dynamic sound.
I’ve mainly used Suno to mess about so I didn’t want to pay for the upgrade.
If there’s ever a need, you could try whatever open generation models use for post processing.