Sorry, you need to enable JavaScript to visit this website.

DRUM TRANSCRIPTION FROM POLYPHONIC MUSIC WITH RECURRENT NEURAL NETWORKS

Citation Author(s):
Richard Vogl, Matthias Dorfer, Peter Knees
Submitted by:
Richard Vogl
Last updated:
9 March 2017 - 6:57pm
Document Type:
Presentation Slides
Document Year:
2017
Event:
Presenters:
Richard Vogl
Paper Code:
2635
 

Automatic drum transcription methods aim at extracting a symbolic representation of notes played by a drum kit in audio recordings. For automatic music analysis, this task is of particular interest as such a transcript can be used to extract high level information about the piece, e.g., tempo, downbeat positions, meter, and genre cues. In this work, an approach to transcribe drums from polyphonic audio signals based on a re- current neural network is presented. Deep learning techniques like dropout and data augmentation are applied to improve the generalization capabilities of the system. The method is evaluated using established reference datasets consisting of solo drum tracks as well as drums mixed with accompaniment. The results are compared to state-of-the-art approaches on the same datasets. The evaluation reveals that F-measure values higher than state of the art can be achieved using the proposed method.

up
0 users have voted: