Skip to content

YvesChu/Musda

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

Musda

We present Musda: Music data augmentation techniques for boosting performance on music generation tasks.

Musda consists six simple but powerful operations: random addition, random shift, random remove, duration float, velocity float and transposition.

On music generation tasks, we show that Musda improves performance and demonstrates particularly strong results for small music datasets in both qualitative and quantitative evaluation.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors