Close menu


Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Electric Guitar Sound Restoration with Diffusion Models

This is the latest version of this item.

Mo, Ronald K. (2023) Electric Guitar Sound Restoration with Diffusion Models. In: DMRN+18: Digital Music Research Network One-day Workshop 2023, 19 Dec 2023, Queen Mary University of London, London, UK. (Unpublished)

Item Type: Conference or Workshop Item (Speech)


This work aims to investigate the potential of employing Denoising diffusion probabilistic models, commonly referred to as diffusion models, to revert a processed electric guitar recording to its original, unaltered form while retaining all the expressive elements of the performance such as dynamics and articulation. Specifically, a parallel dataset is constructed, containing both the unprocessed and processed versions of the guitar recordings, which is used for training a diffusion model. To preserve the expressiveness, the model is conditioned on the processed guitar recording when restoring the raw guitar sound. This research has the potential to enhance the accuracy of various music information retrieval tasks, such as automatic
music transcription.

Electric Guitar Sound Restoration with Diffusion Models.pdf

Download (579kB) | Preview

More Information

Depositing User: Ronald Mo


Item ID: 17200
Official URL:

Users with ORCIDS

ORCID for Ronald K. Mo: ORCID iD

Catalogue record

Date Deposited: 09 Jan 2024 09:17
Last Modified: 09 Jan 2024 09:30


Author: Ronald K. Mo ORCID iD

University Divisions

Faculty of Technology > School of Computer Science


Computing > Artificial Intelligence
Performing Arts > Music

Actions (login required)

View Item (Repository Staff Only) View Item (Repository Staff Only)

Available Versions of this Item