ASMD: an automatic framework for compiling multimodal datasets with audio and scores
This framework addresses the problem of dataset management for researchers in music computing, though it is incremental as it builds on existing datasets and tools.
The paper tackles the challenge of reproducibility and generalization in music computing research by introducing ASMD, an open-source Python framework that automatically compiles multimodal datasets with audio and scores, providing a Python API for dataset access through Boolean set operations based on attributes like composers and instruments.
This paper describes an open-source Python framework for handling datasets for music processing tasks, built with the aim of improving the reproducibility of research projects in music computing and assessing the generalization abilities of machine learning models. The framework enables the automatic download and installation of several commonly used datasets for multimodal music processing. Specifically, we provide a Python API to access the datasets through Boolean set operations based on particular attributes, such as intersections and unions of composers, instruments, and so on. The framework is designed to ease the inclusion of new datasets and the respective ground-truth annotations so that one can build, convert, and extend one's own collection as well as distribute it by means of a compliant format to take advantage of the API. All code and ground-truth are released under suitable open licenses.