[Stavros Korokithakis] finds the experience of falling asleep to fairy tales soothing, and this has resulted in a fascinating project that indulges this desire by using machine learning to generate mildly incoherent fairy tales and read them aloud. The result is a fantastic sort of automated, machine-generated audible sleep aid. Even the logo is machine-generated!
The project leverages the natural language generation abilities of OpenAI’s GPT-3 to create fairytale-style content that is just coherent enough to sound natural, but not quite coherent enough to make a sensible plotline. The quasi-lucid, dreamlike result is perfect for urging listeners to imagine pleasant nonsense (thanks to Nathan W Pyle for that term) as they drift off to sleep.
We especially loved reading about the methods and challenges [Stavros] encountered while creating this project. For example, he talks about how there is more to a good-sounding narration than just pointing a text-to-speech engine at a wall of text and mashing “GO”. A good episode has things like strategic pauses, background music, and audio fades. That’s where pydub — a Python library for manipulating audio — came in handy. As for the speech, text-to-speech quality is beyond what it was even just a few years ago (and certainly leaps beyond machine-generated speech in the 80s) but it still took some work to settle on a voice that best suited the content, and the project gradually saw improvement.
Deep Dreams Podcast has a GitLab repository if you want to see the code that drives it all, and you can go to the podcast itself to give it a listen.
AI beaming thoughts directly into our ears while we sleep? Hmmmm
Hail hydra
No way I can go to sleep to those: I want to know what happens next!
Hol’ up fren’… you’ll have Philip Jose Farmer re-inventing Lewis Carrol as some mechanical difference engine AI prototype built by Captain Nemo or something.
Now I just need a computer to rock me to sleep. No seriously, I’d like that.
Needs a dungeon synth backing track and some slow wave binaural phasing then it would be perfect.
Could put a lot of journalists out of work.
I don’t think journalists traditionally tell bedtime stories- I think their jobs are secure.
I dunno, you could probably replace a few dozen in the “too off the the wall to even parody” alt right media by training it on Qanon drivel and whaddabout Hillary’s email diatribes.
This reminds me of a short story I read before. Where the main character is an author of books but he didn’t write the stories. The main character stole excellent stories that were generated from a.i. and claimed them as his own work.
Maybe the monkeys at the typewriters will instead turn out to be a.i.
“It was only an ‘opeless fancy.
It passed like an Ipril dye,
But a look an’ a word an’ the dreams they stirred!
They ‘ave stolen my ‘eart awye!
The tune had been haunting London for weeks past. It was one of countless similar songs published for the benefit of the proles by a sub-section of the Music Department. The words of these songs were composed without any human intervention whatever on an instrument known as a versificator.”
The Gilgamesh episode – I wasnt sure if I was listening to AI reading me the bible, Brokeback Mountain, or Lord of the Rings