PyMAiVAR: An open-source Python suit for audio-image representation in human action recognition

Authors

Muhammad B. Shaikh, Edith Cowan UniversityFollow
Douglas Chai, Edith Cowan UniversityFollow
Syed M. S. Islam, Edith Cowan UniversityFollow
Naveed Akhtar

Document Type

Journal Article

Publication Title

Software Impacts

Volume

17

Publisher

Elsevier

School

School of Science / School of Engineering

RAS ID

58302

Funders

Edith Cowan University / Australia and Higher Education Comission (HEC) of Pakistan / Australian Government

Comments

Shaikh, M. B., Chai, D., Islam, S. M. S., & Akhtar, N. (2023). PyMAiVAR: An open-source Python suit for audio-image representation in human action recognition. Software Impacts, 17, article 100544. https://doi.org/10.1016/j.simpa.2023.100544

Abstract

We present PyMAiVAR, a versatile toolbox that encompasses the generation of image representations for audio data including Wave plots, Spectral Centroids, Spectral Roll Offs, Mel Frequency Cepstral Coefficients (MFCC), MFCC Feature Scaling, and Chromagrams. This wide-ranging toolkit generates rich audio-image representations, playing a pivotal role in reshaping human action recognition. By fully exploiting audio data's latent potential, PyMAiVAR stands as a significant advancement in the field. The package is implemented in Python and can be used across different operating systems.

DOI

10.1016/j.simpa.2023.100544

Related Publications

Shaikh, M. (2023). Multimodal human action recognition using deep learning. Edith Cowan University. Retrieved from https://ro.ecu.edu.au/theses/2749

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.