
Con los años, la consecutiva introducción de amplificadores y pedales ha diversificado cada vez más las posibilidades tonales para los guitarristas. Aunque los simuladores digitales lograron disminuir inmensamente el gasto monetario en equipamiento, ciertos componentes analógicos resisten su digitalización. Este Trabajo Fin de Grado se enfoca en emular estos dispositivos mediante aprendizaje profundo. Para ello, implementamos una aplicación desplegada en una Raspberry Pi 5, que encapsulada y acompañada de una interfaz de audio y de un circuito de entrada y salida, actúa como un pedal digital más integrado en la señal de la guitarra. Esta fusión de informática y electrónica proporciona una solución innovadora, eficiente y accesible para recrear tonos analógicos.
Over the years, the consecutive introduction of amplifiers and pedals has increasingly diversified tonal possibilities for guitarists. Although digital simulators have immensely reduced the monetary expense of equipment, certain analog components resist digitalization. This Bachelor's Thesis focuses on emulating these devices through deep learning. To this end, we implemented an application deployed on a Raspberry Pi 5, which, when encapsulated and accompanied by an audio interface and an input/output circuit, acts as an integrated digital pedal in the guitar signal chain. This fusion of computer science and electronics provides an innovative solution for recreating analog tones in an efficient and accessible way.
Memoria del Trabajo Fin de Grado defendido el 4 de julio de 2024 para la obtención del título de Graduado en Ingeniería Informática, por la Universidad de La Rioja. Diapositivas de la charla para las Jornadas de Jóvenes Investigadores 2025, celebrada el dia 10 de abril de 2025. AmpEmulatorModel (modelo de inteligencia artificial) AmpEmulatorPlugin (aplicación/plugin VST3)
JUCE, black-box modelling, Raspberry Pi 5, deep learning, convolutional neural network, electric guitar amp emulation, real time audio processing, Wavenet, VST3
JUCE, black-box modelling, Raspberry Pi 5, deep learning, convolutional neural network, electric guitar amp emulation, real time audio processing, Wavenet, VST3
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
