Using Machine Learning to generate rap lyrics

Re:Using Machine Learning to generate rap lyrics by hooande on Friday November 06, 2015 @04:01PM (#10522005)

There are some very interesting techniques in the linked paper, particularly the moving average alternative to bag of words and the use of RankSVM.

But this generated sample (verbatim) isn't rap, it's just rhyming words:

  You've been a survivor and we love you so much
  You don't know me - I kill everyone who show love
  I I know you all love me to be sad and shit but
  Will lead you to peace to love to unity and havin' fun
  And say I love you momma and you are not alone
  To say I love you! I love you! Forever so!
  I say I love you you say it don't show
  Tell me you love me I love you baby oh oh
  Oh baby I love you
  Can I love you baby? 
  What we about to do
  ''HOW COULD YOU JUST LEAVE ME AND LOVE HIM OUT THE BLUE?!''
  But your on it too so you tell me you love me too
  Let your love home you Let me move you tonight Baby
  I know you love it when I shine I'm waitin' ..
  And I think I love him I love him just like I raised him
  I love rap no matter how much I say I hate it

Contrary to popular belief, rap lyrics do contain insight and capture cultural moments. The gap there relates to the question of whether or not computer programs can be 'creative'. This line from the linked paper also sheds light on the quality of these lyrics:

"In terms of quantitative rhyme density, the produced lyrics outperform best human rappers by 21%"

I'm not sure if sheer rhyme density is how rap or any other form of music should be judged, but if it is then human rappers are only 79% as good as the best machine MCs.

[ Parent | on HN ]

Re:Using Machine Learning to generate rap lyrics by fluxquanta on Friday November 06, 2015 @04:46PM (#10522273)

>Contrary to popular belief, rap lyrics do contain insight and capture cultural moments.

This, to me, is the most important part of rap. Rhymes are secondary. There's something really satisfying about listening to a catchy rap song then looking up the lyrics on genius.com and seeing how clever and layered the wordplay is, depending on the quality of the artist, of course.

[ Parent | on HN ]

Re:Using Machine Learning to generate rap lyrics by sehr on Friday November 06, 2015 @05:07PM (#10522389)

And on the flipside, a lot of rappers are loved for their flow more than their words! Travis Scott, Migos & Young Thug immediately come to mind for flow/overall sound/aesthetic > lyrics (even though they have their moments).

And that's especially true given the huge increase in attention given to producers, to the point where people are more excited about collabs between producers & rappers rather than just rappers themselves

Raps super diverse, and super fun to watch evolve

[ Parent | on HN ]