Data-driven estimation of traditional frame drum construction specifications

Vryzas N, Bountourakis V, Pagonis A. Data-driven estimation of traditional frame drum construction specifications. In: Express Paper. Audio Engineering Society; 2025. Paper 340. Available from: https://aes.org/publications/elibrary-page/?id=22891

@inproceedings{Vryzas2025_22891,
  author = {Vryzas, Nikolaos and Bountourakis, Vasileios and Pagonis, Antonis},
  title = {{Data-driven estimation of traditional frame drum construction specifications}},
  note = {Paper 340},
  year = {2025},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=22891}
}

TY  - CPAPER
TI  - Data-driven estimation of traditional frame drum construction specifications
AU  - Vryzas, Nikolaos
AU  - Bountourakis, Vasileios
AU  - Pagonis, Antonis
M1  - Paper 340
PY  - 2025
DA  - 2025/05/12
UR  - https://aes.org/publications/elibrary-page/?id=22891
PB  - Audio Engineering Society
LA  - en
AB  - This research aims to provide a systematic approach for the analysis of geometrical and material characteristics of traditional frame drums using deep learning. A data-driven approach is used, integrating supervised and unsupervised feature extraction techniques to associate measurable audio features with perceptual attributes. The methodology involves the training of convolutional neural networks on Mel-Scale spectrograms to estimate wood type (classification), diameter (regression), and depth (regression). A multi-labeled dataset containing recorded samples of frame drums of different specifications is used for model training and evaluation. Hierarchical classification is explored, incorporating playing techniques and environmental factors. Handcrafted features enhance interpretability, helping determine the impact of construction attributes on sound perception, ultimately aiding instrument design. Data augmentation techniques, including pitch alterations, additive noise, etc. are introduced to expand the generalization of the approach and dataset expansion.
ER  -