Guitar Effects Recognition and Parameter Estimation With Convolutional Neural Networks

Comunità, Marco; Stowell, Dan; Reiss, Joshua D.

doi:10.17743/jaes.2021.0019

Cited by 8 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parallel KLANN and the parallel-series KLANN are evaluated with two configurations: small and large. The small We compare state-of-the-art convolutional and recurrent networks called the GCNTF [9] and LSTM [4], respectively. We use the implementation provided in [9].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

KLANN: Linearising long-term dynamics in nonlinear audio effects using Koopman networks

Huhtala,

Juvela,

Schlecht

2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

“…Sebastian J. Schlecht is also with the Media Lab, Department of Art and Media, Aalto University, FI-02150 Espoo, Finland. made progress towards modeling long-term dependencies [9], but the models are still relatively expensive and hard to interpret.…”

Section: Introductionmentioning

confidence: 99%

KLANN: Linearising long-term dynamics in nonlinear audio effects using Koopman networks

Huhtala,

Juvela,

Schlecht

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…An example of the four timefrequency representations applied to the same audio sample is shown in Fig. 2 and were based on [13]. The total number of weights of the CNN used for classification ranged from 192,587 (chromagram) to 10,436,683 (spectrogram) with 1,368,139 for MFCCs and 1,597,515 for GFCCs.…”

Section: Architecturementioning

confidence: 99%

“…So far, only three previous works exist: Jürgens et al [12] pioneered this task using shallow neural networks combined with specifically designed features for each guitar effect, achieving or surpassing the (presumed) performance of a human expert. Comunità et al [13] used convolutional neural networks (CNNs) to extract the parameter settings of different implementations of distortion-related guitar effects from monophonic and polyphonic audio samples, achieving below 0.1 root-mean-square error in all cases. In [14], a CNN was used for the classification of guitar effects from instrument mixes as well as the extraction of their parameter settings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Hinrichs

Gerkens

Lange

et al. 2022

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Guitar effects are commonly used in popular music to shape the guitar sound to fit specific genres, or to create more variety within musical compositions. The sound not only is determined by the choice of the guitar effect, but also heavily depends on the parameter settings of the effect. Previous research focused on the classification of guitar effects and extraction of their parameter settings from solo guitar audio recordings. However, more realistic is the classification and extraction from instrument mixes. This work investigates the use of convolution neural networks (CNNs) for the classification and parameter extraction of guitar effects from audio samples containing guitar, bass, keyboard, and drums. The CNN was compared to baseline methods previously proposed, like support vector machines and shallow neural networks together with predesigned features. On two datasets, the CNN achieved classification accuracies $$1-5\,\%$$ 1 - 5 % above the baseline accuracy, achieving up to $$97.4\, \%$$ 97.4 % accuracy. With parameter values between 0.0 and 1.0, mean absolute parameter extraction errors of below 0.016 for the distortion, below 0.052 for the tremolo, and below 0.038 for the slapback delay effect were achieved, matching or surpassing the presumed human expert error of 0.05. The CNN approach was found to generalize to further effects, achieving mean absolute parameter extraction errors below 0.05 for the chorus, phaser, reverb, and overdrive effect. For sequentially applied combinations of distortion, tremolo, and slapback delay, the mean extraction error slightly increased from the performance for the single effects to the range of 0.05 to 0.1. The CNN was found to be moderately robust to noise and pitch changes of the background instrumentation suggesting that the CNN extracted meaningful features.

show abstract

Classification of Guitar Effects and Extraction of Their Parameter Settings from Instrument Mixes Using Convolutional Neural Networks

Hinrichs

Gerkens

Östermann

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Guitar Effects Recognition and Parameter Estimation With Convolutional Neural Networks

Cited by 8 publications

References 20 publications

KLANN: Linearising long-term dynamics in nonlinear audio effects using Koopman networks

KLANN: Linearising long-term dynamics in nonlinear audio effects using Koopman networks

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

Classification of Guitar Effects and Extraction of Their Parameter Settings from Instrument Mixes Using Convolutional Neural Networks

Contact Info

Product

Resources

About