A Fully Convolutional Deep Auditory Model for Musical Chord Recognition
Sprache des Vortragstitels:
Englisch
Original Tagungtitel:
IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
Sprache des Tagungstitel:
Englisch
Original Kurzfassung:
Chord recognition systems depend on robust feature ex-
traction pipelines. While these pipelines are traditionally
hand-crafted, recent advances in end-to-end machine learn-
ing have begun to inspire researchers to explore data-driven
methods for such tasks. In this paper, we present a chord
recognition system that uses a fully convolutional deep audi-
tory model for feature extraction. The extracted features are
processed by a Conditional Random Field that decodes the
final chord sequence. Both processing stages are trained auto-
matically and do not require expert knowledge for optimising
parameters. We show that the learned auditory system ex-
tracts musically interpretable features, and that the proposed
chord recognition system achieves results on par or better
than state-of-the-art algorithms.
Forschungs-