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

facebooktwittermailshare

INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING

Abstract: 

We measure the effect of small amounts of systematic and
random label noise caused by slightly misaligned ground truth
labels in a fine grained audio signal labeling task. The task
we choose to demonstrate these effects on is also known as
framewise polyphonic transcription or note quantized multi-
f0 estimation, and transforms a monaural audio signal into a
sequence of note indicator labels. It will be shown that even
slight misalignments have clearly apparent effects, demonstrating a great sensitivity of convolutional neural networks
to label noise. The implications are clear: when using convolutional neural networks for fine grained audio signal label-
ing tasks, great care has to be taken to ensure that the annotations have precise timing, and are free from systematic or
random error as much as possible - even small misalignments
will have a noticeable impact.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
23 April 2018 - 9:01pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Rainer Kelz
Document Year:
2018
Cite

Document Files

large_poster_96x48.pdf

(59 downloads)

Subscribe

[1] , "INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3156. Accessed: Aug. 18, 2018.
@article{3156-18,
url = {http://sigport.org/3156},
author = { },
publisher = {IEEE SigPort},
title = {INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING},
year = {2018} }
TY - EJOUR
T1 - INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3156
ER -
. (2018). INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING. IEEE SigPort. http://sigport.org/3156
, 2018. INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING. Available at: http://sigport.org/3156.
. (2018). "INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING." Web.
1. . INVESTIGATING LABEL NOISE SENSITIVITY OF CONVOLUTIONAL NEURAL NETWORKS FOR FINE GRAINED AUDIO SIGNAL LABELLING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3156