Abstract
Detecting musical onsets is the first step for many aspects of
music analysis, but still lacks accuracy for polyphonic music signals. We
perform an initial exploration of the effectiveness of using Convolutional
Neural Networks for this task. On a dataset of about 100 minutes of
music with 26k annotated onsets, our first experiments slightly surpass
the best existing method while requiring less manual preprocessing. The
results suggest new directions for improving on the state of the art in
onset detection.
| Original language | English |
|---|---|
| Title of host publication | 6th International Workshop on Machine Learning and Music (MML), in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML) |
| Number of pages | 4 |
| Publication status | Published - Sept 2013 |
Fields of science
- 202002 Audiovisual media
- 102 Computer Sciences
- 102001 Artificial intelligence
- 102003 Image processing
- 102015 Information systems
JKU Focus areas
- Computation in Informatics and Mathematics
- Engineering and Natural Sciences (in general)