Jazz trio database: automated annotation of jazz piano trio recordings processed using audio source separation

HIGHLIGHTS

• What: The authors focus primarily on timing, as this enables the analysis of interesting group-level musical features, such as interaction and synchronization. The methodology used by the PiJAMA authors has several similarities with the contribution : curated playlists of relevant music were developed by scraping discographic services and audio was downloaded from YouTube. The authors demonstrate in 4.3.3 that filtering the piano audio improved the accuracy of the onset annotation pipeline compared to using the raw audio, and that this particular frequency range performed better than an alternative, quantitatively "narrower" range. The authors fitted the . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.