Skip to main content

Table 5 \(95\,\%\) 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 distortion and tremolo 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) Distortion + tremolo

 

Gain

Tone

Depth

Frequency

CNN + chromagram

0.096 ± 0.002

0.133 ± 0.0039

0.094 ± 0.0024

0.099 ± 0.0023

CNN + GFCCs

0.077 ± 0.0007

0.085 ± 0.0008

0.056 ± 0.0034

0.083 ± 0.0011

CNN + MFCCs

0.079 ± 0.001

0.085 ± 0.003

0.084 ± 0.0029

0.097 ± 0.0039

CNN + spectrogramm

0.076 ± 0.0013

0.081 ± 0.0007

0.072 ± 0.0054

0.069 ± 0.0039