Reference : Generating 3D Dances From Music Using Deep Neural Networks
Dissertations and theses : Bachelor/master dissertation
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/50481
Generating 3D Dances From Music Using Deep Neural Networks
English
Dupont, Elona mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > CVI2 >]
Jun-2021
University of Luxembourg, ​​Luxembourg
Master in Information and Computer Sciences
Aouada, Djamila mailto
Kacem, Anis mailto
Baptista, Renato mailto
van der Torre, Leon mailto
[en] deep learning ; 3D ; dance ; LSTM ; computer science
[en] This thesis focuses on the generation of original and unique 3D dances given a music
using deep neural networks. A state of the art model (Dance Revolution) was adapted
to take as input 3D data. Then it was trained using the recently published AIST++
dataset. At the generation phase, the model is able to generate credible dances. This
was achieved by introducing a novel audio data augmentation technique that modifies the
harmonic content of a song without changing the rhythmic content. This method allowed
for an increase in the number of training epochs before the LSTM network converges to
a static pose. Additionally, a novel method to evaluate the coherence of the generated
dances with respect to the style of music is proposed. The comparison is based on key
dance moves that are identified using the matrix profile. Using this method to evaluate
the dances, it was found that the model generate coherent dances with respect to the
dominant styles of music in the dataset.
http://hdl.handle.net/10993/50481

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Generating 3D Dances From Music Using Deep Neural Networks.pdfAuthor postprint3.07 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.