Building a Music Recommender with Deep Learning
mattmurray.net
Building a Music Recommender with Deep Learning
1–10 of 74 posts
Re: Building a Music Recommender with Deep Learning
#2hugged?
Re: Building a Music Recommender with Deep Learning
#3Very cool post! :)
"Simple" method (good ol' spectrograms, and something people can realistically actually reproduce without requiring a GPU farm), and great results!
Re: Building a Music Recommender with Deep Learning
#4There is a simple music recommender webapp shown in the video. From your model you got a python function that maps one song (e.g. by artist,title) to other songs.
What is the fastest way to build this interactive webapp (for internal, experimental) use?
Re: Building a Music Recommender with Deep Learning
#5This is interesting, but fairly easy to confuse. Esp. would be interesting to see what results come up when you use modified "artistic" spectographs like that of Windowlicker by Aphex Twin [1]. One thing I've learned from years of having worked with audio and images is that image representations of audio are horrible representations of it (other than for temporal changes).
The results are good though! Good work! :D
[1] http://twistedsifter.com/2013/01/hidden-images-embedded-into...
Re: Building a Music Recommender with Deep Learning
#6Site is overloaded, cached version
http://webcache.googleusercontent.com/search?q=cache:http://...
Re: Building a Music Recommender with Deep Learning
#7This is interesting.
My first thought was to wonder how a LSTM would do. Once might think it would be a better representation for music? There's some models which use convolutional layers along with a LSTM for video representation (eg [1]) and it would be interesting to see if convolutions are useful for capturing similar themes of music.
I wonder if one could build a music embedding (word2vec style) and use similarities in the embedding space as recommendations? The obvious objective function would be skip-gram, but there might be more interesting objectives there too.
[1] https://github.com/loliverhennigh/Convolutional-LSTM-in-Tens...
Re: Building a Music Recommender with Deep Learning
#8> Wouldn’t it be cool if you could discover music that was released a few years ago that sounds similar to a new song that you like?
Perhaps. But of course, this is likely to put the user literally into an "echo chamber" :)
Re: Building a Music Recommender with Deep Learning
#9> It did a really good job classifying trance music while at the other end of the scale was hip hop / R&B with 61%, which is still almost 6 times better than randomly assigning a genre to the image. I suspect that there’s some crossover between hip hop, breakbeat and dancehall and that might have resulted in a lower classification accuracy.
The first step to analyze this is to make a confusion matrix, [1]. It would be nice if the article included it.
Re: Building a Music Recommender with Deep Learning
#10Wow thanks for sharing + reading my blog post! I did this for my final project on the Data Science bootcamp at Metis [1] this spring.