Parametric Neural Amp Modeling with Active Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912618585784320 |
|---|---|
| author | Grötschla, Florian Jiao, Longxiang Lanzendörfer, Luca A. Wattenhofer, Roger |
| author_facet | Grötschla, Florian Jiao, Longxiang Lanzendörfer, Luca A. Wattenhofer, Roger |
| contents | We introduce Panama, an active learning framework to train parametric guitar amp models end-to-end using a combination of an LSTM model and a WaveNet-like architecture. With \model, one can create a virtual amp by recording samples that are determined through an ensemble-based active learning strategy to minimize the amount of datapoints needed (i.e., amp knob settings). Our strategy uses gradient-based optimization to maximize the disagreement among ensemble models, in order to identify the most informative datapoints. MUSHRA listening tests reveal that, with 75 datapoints, our models are able to match the perceptual quality of NAM, the leading open-source non-parametric amp modeler. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26564 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parametric Neural Amp Modeling with Active Learning Grötschla, Florian Jiao, Longxiang Lanzendörfer, Luca A. Wattenhofer, Roger Machine Learning Artificial Intelligence We introduce Panama, an active learning framework to train parametric guitar amp models end-to-end using a combination of an LSTM model and a WaveNet-like architecture. With \model, one can create a virtual amp by recording samples that are determined through an ensemble-based active learning strategy to minimize the amount of datapoints needed (i.e., amp knob settings). Our strategy uses gradient-based optimization to maximize the disagreement among ensemble models, in order to identify the most informative datapoints. MUSHRA listening tests reveal that, with 75 datapoints, our models are able to match the perceptual quality of NAM, the leading open-source non-parametric amp modeler. |
| title | Parametric Neural Amp Modeling with Active Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.26564 |