Manifold Learning Methods for Visualization and Browsing of Drum Machine Samples

Shier J, McNally K, Tzanetakis G, Brooks KG. Manifold Learning Methods for Visualization and Browsing of Drum Machine Samples. J Audio Eng Soc. 2021;69(1/2):40-53. doi:10.17743/jaes.2020.0064

@article{Shier2021_21015,
  author = {Shier, Jordie and McNally, Kirk and Tzanetakis, George and Brooks, Ky Grace},
  title = {{Manifold Learning Methods for Visualization and Browsing of Drum Machine Samples}},
  journal = {Journal of the Audio Engineering Society},
  volume = {69},
  number = {1/2},
  pages = {40--53},
  year = {2021},
  month = jan,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2020.0064},
  url = {https://doi.org/10.17743/jaes.2020.0064}
}

TY  - JOUR
TI  - Manifold Learning Methods for Visualization and Browsing of Drum Machine Samples
AU  - Shier, Jordie
AU  - McNally, Kirk
AU  - Tzanetakis, George
AU  - Brooks, Ky Grace
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 69
IS  - 1/2
SP  - 40
EP  - 53
PY  - 2021
DA  - 2021/01/06
DO  - 10.17743/jaes.2020.0064
UR  - https://doi.org/10.17743/jaes.2020.0064
PB  - Audio Engineering Society
LA  - en
AB  - The use of electronic drum samples is widespread in contemporary music productions, with music producers having an unprecedented number of samples available to them. The task of organizing and selecting from these large collections can be challenging and time consuming, which points to the need for improved methods for user interaction. This paper presents a system that computationally characterizes and organizes drum machine samples in two dimensions based on sound similarity. The goal of the work is to support the development of intuitive drum sample browsing systems. The methodology presented explores time segmentation, which isolates temporal subsets from the input signal prior to audio feature extraction, as a technique for improving similarity calculations. Manifold learning techniques are compared and evaluated for dimensionality reduction tasks, and used to organize and visualize audio collections in two dimensions. This methodology is evaluated using a combination of objective and subjective methods including audio classification tasks and a user listening study. Finally, we present an open-source audio plug-in developed using the JUCE software framework that incorporates the findings from this study into an application that can be used in the context of a music production environment.
ER  -