For example, here's a quick clip from a synth I've been using in recent weeks:
https://vocaroo.com/125tAD40Gl6d
It sounds almost like a real voice, and that's just using the default settings, without any effort to tweak it further to improve the realism.
To boot, isn't this the fidelity vs fun argument of videogames again, too?
Madonna's "Ray of Light" is still a good song without her; William Orbit is a master producer after all. I hope we see a refocusing away from personalities to producers out of this.
Even just from a technology point of view, I find it fascinating to see how the envelope is being pushed via machine learning models.
Let me just point out the nuance that many people, including myself, appreciate both types of music.
Too many people express this belief. It does not seem plausible, statistically. I wonder what made it so widespread.
What really sold it to me was listening to some beautifully crafted covers from this YouTube channel: https://www.youtube.com/watch?v=KX0lcVr9ugI
Prior to this, I'd been experimenting with pitch-shifting the output of Google's Text-to-Speech service (https://cloud.google.com/text-to-speech), which was quite interesting and somewhat pleasant sounding for spoken word vocals, but didn't really have the range or expressiveness I was looking for more generally.