@wilbr yeah sorry for better or worse I live-toot my experiments on mastodon before it all goes through the filter of "try to make this accessible for people who are not allison"
@sluglife not yet, still just playing around. hoping to make a demo and release code in a few weeks
similar problems with /ʒ/ ("genre" comes out as ?ehnuh where <?> is a consonant described as a "voiced alveolar fricative stop" with a hint of velar thrown in). probably because these sounds combine be less than 1% of all sounds and might not be present more than a handful of times in the training set. I might have to think about partitioning differently or augmenting the data set to even out the distribution
@sluglife it is amusing how easy it is to compare these mistakes to the mistakes of people who learn english as adults! (though I'm definitely not claiming that the processes are internally similar in any way)
my seq2seq network for predicting phonetic features at from character strings after 10 epochs is at 99% accuracy on the validation set and pronounces (e.g.) "fediverse" (not in training set) almost flawlessly (I'll transcribe the features as "fidiverz") but seems to consistently mess up on interdental fricatives ("theorizing" comes out as "feruhzing," "lathe" comes out as "lat-tee," "this" comes out as "sis")
odd because it's an example of the map becoming the territory. the whole point of contemporary nlproc is to be able to work with the meaning of a sentence as something other than the sum of the semantics of its component words, but in this case, the sentences on the left are shown as being "similar" to one another *simply because of their lexical similarities*. it's hard to think of an actual human speech context where "I love tacos" means anything remotely close to "we are all tacos"
ran across this very good overview of text generation techniques with neural networks https://blog.usejournal.com/generating-natural-language-text-with-neural-networks-e983bb48caad though it's notable mostly for this very odd/hilarious illustration of "meaning space"
For the holidays, you could say thank you to some of the people who write free software you use, especially software that isn't hugely popular.
Those of us who write little-known software may go for months without hearing from a user, and it can be a little de-motivating.
Hearing from someone who actually uses one's software gives an energising jolt that can carry one through several weeks of darkness and cold and wet.
@enkiv2 @mewo2 maybe that's it, I dunno. this residency has separate application forms for a number of categories (there's "film" and "poetry" and "visual art" and several others and then "interdisciplinary"). only the "interdisciplinary" form has this question. (I was only filling in the "interdisciplinary" form because I never get accepted when I apply for things in the "poetry" category and "interdisciplinary" is often the arts code-word for "if you use a computer apply in this category")
@zwol I get that, I just find it difficult to conceive of an artist who (a) would choose to apply for a residency specifically in the multidisciplinary category but (b) has two or more practices that never interact with each other enough to be considered "interdisciplinary"
@enkiv2 @mewo2 right—I am also "multidisciplinary" in the sense that I make computer-generated poetry (discipline A) and also (e.g.) do the dishes every morning (discipline B). if these two disciplines are truly separate, I don't understand why it would be important to mention being "multidisciplinary" on an arts residency application, since surely you would just apply in the "computer-generated poetry" category or the "dishwashing" category instead?
@mewo2 I guess I'm having trouble thinking of anyone's arts practice that corresponds to that "multidisciplinary" description that doesn't also significantly bleed into "interdisciplinary" (because otherwise why would you be "multidisciplinary" to begin with, if not to set up some kind of contrast/interpolation between the disciplines in question?)
poet, programmer, game designer, computational creativity researcher. assistant arts professor at NYU ITP. she/her.
Follow friends and discover new ones. Publish anything you want: links, pictures, text, video. This server is run by the main developers of the Mastodon project. Everyone is welcome as long as you follow our code of conduct!