THE CONFERENCE
FOR AUTHORS
FOR PARTICIPANTS

Timezone: »

 
Poster
Dance Dance Convolution
Chris Donahue · Zachary Lipton · Julian McAuley

Wed Aug 09 01:30 AM -- 05:00 AM (PDT) @ Gallery #104
in Posters Wed »

Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players perform steps on a dance platform in synchronization with music as directed by on-screen step charts. While many step charts are available in standardized packs, players may grow tired of existing charts, or wish to dance to a song for which no chart exists. We introduce the task of learning to choreograph. Given a raw audio track, the goal is to produce a new step chart. This task decomposes naturally into two subtasks: deciding when to place steps and deciding which steps to select. For the step placement task, we combine recurrent and convolutional neural networks to ingest spectrograms of low-level audio features to predict steps, conditioned on chart difficulty. For step selection, we present a conditional LSTM generative model that substantially outperforms n-gram and fixed-window approaches.

Author Information

Chris Donahue (University of California, San Diego)
Zachary Lipton (UCSD)
Julian McAuley (UCSD)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors