Skip to main content

Table 7 \(95\,\%\) confidence intervals of the mean absolute error of the CNN across the fivefold cross-validation of the parameter extraction and all volumes. Results are reported for all time-frequency representations and the combination of tremolo and slapback delay effect

From: Convolutional neural networks for the classification of guitar effects and extraction of the parameter settings of single and multi-guitar effects from instrument mixes

(a) Tremolo + slapback delay

 

Depth

Frequency

Time

Mix

CNN + chromagram

0.106 ± 0.0017

0.085 ± 0.0038

0.152 ± 0.0024

0.128 ± 0.0017

CNN + GFCCs

0.071 ± 0.0018

0.09 ± 0.0036

0.106 ± 0.0029

0.067 ± 0.0017

CNN + MFCCs

0.092 ± 0.0034

0.098 ± 0.0046

0.084 ± 0.0017

0.064 ± 0.0011

CNN + spectrogramm

0.069 ± 0.0023

0.083 ± 0.0028

0.083 ± 0.0019

0.058 ± 0.0017