PyMAiVAR: An open-source Python suite for audio-image representation in human action recognition
Muhammad Bilal Shaikh, Douglas Chai, Syed Mohammed Shamsul Islam, Naveed Akhtar · Software Impacts · 2023
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. • Introducing PyMAiVAR, a pioneering audio-image representation tool for human action recognition. • PyMAiVAR facilitates the creation of six unique audio-image representations. • The library’s design allows for the development and incorporation of more abstract features. • Offering researchers, a flexible platform for further improvements and potential integration with other functionalities. • Supports cross-platform development, uses Python 3, and released under GPL license to promote open and reproducible research. • High composability enables seamless integration with other libraries, enhancing versatility and facilitating diversity.