• Description
  • Project
  • Repository
  • Technical Details
• Acknowledgements
• License

GS-Detector performs automatic guitar string detection by exploiting the spectral feature of real strings known as inharmonicity, for applications such as automatic tablature transcription. The algorithm requires minimal data for adaptation and is designed for use only with monophonic guitar audio recordings, while assuming that the pitch, as well as the onset and offset timestamps of the played notes, are known.

The code in this repository is contained in two Jupyter Notebooks, namely main.ipynb and supplement.ipynb. The former implements and evaluates the proposed guitar string detection algorithm, while the latter demonstrates the process of computing the inharmonicity coefficient. The Datasets utilized for the evaluation of the algorithm are provided in the corresponding directory. Lastly, a related unpublished paper is also included in the repository for reference.

This project was developed exclusively within the computing environment of Google Colaboratory, thus the specific version of Python used and any package requirements are subject to the up-to-dateness of the service at the time of development. To run the notebooks in your own working environment, please refer to the associated code sections and make any necessary adjustments.

The datasets included in this repository are sourced from the IDMT-SMT-Guitar dataset by Christian Kehling, Andreas Männchen and Arndt Eppler. Each dataset directory provided in this repository corresponds to a specific directory within the original dataset as follows:

Datasets/Bridge Pickup  → IDMT-SMT-GUITAR/dataset1/Ibanez Power Strat Clean Bridge HU
Datasets/Middle Pickup → IDMT-SMT-GUITAR/dataset1/Ibanez Power Strat Clean Bridge+Neck SC
Datasets/Neck Pickup    → IDMT-SMT-GUITAR/dataset1/Ibanez Power Strat Clean Neck HU

GS-Detector © 2024 by Alexandros Iliadis is licensed under CC BY 4.0.

This license requires that reusers give credit to the creator. It allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, even for commercial purposes.

See the LICENSE.md file for more details.