Well, hold that thought, what if one-to-one means AI to AI...
15 karma · joined August 9, 2016
On the other hand, this is excellent PR for Opower.
For lyrics, we actually didn't train on Christmas songs. Training data was a large collection of romance novels. (See neural-storyteller by Jamie Kiros). The "Christmas trick" we did was applying a "style shifting" after image captioning and before lyrics generation, where the shifting vector was obtained from ~30 Christmas songs.
For the music generation. Although we are aware of some basic music performing rules, such as melody following chord etc, we actually didn't add this kind of rules.
For the blues scale here's the thing. I didn't really know much about music, so I spent several hours reading things like basicmusictheory.com. It happened to introduce blues so we just used it. But you're right on the relevance between blues and pop: only a very small percentage in our pop music collection is blues, after we ran the scale-checking code.
Our original focus was writing a research paper on hierarchical music generation. Composing a song from an image is just one of the "fun applications" that we spent a little time on, to promote the interestingness of our method. I started Saturday afternoon, and was basically done by Sunday night.
Not sure how to hardcode this.
While it is easy to crawl many songs from the internet, it is a little harder to gather the same amount but with proper genre/style/etc labels, although it is not impossible.
For now there's only one genre, which we call it "the genre of whatever is on the internet". So whatever music files on there, many of them quite "crappy", were used to train the model. Also there are many other problems on how to better structure and flavor the composition.
This is just a very early-stage attempt, as a CS student's fun side project. We are working with people with real musical talent now and hoping to make better songs in the next version.