Capturing the workflows of music information retrieval for repeatability and reuse
Journal of Intelligent Information Systems
| Hi-index | 0.00 |
Conducting valid comparative evaluations of techniques in the field of Music Information Retrieval (MIR)presents particular challenges to MIR researchers due to issues of copyright and data sharing. Further, the interdisciplinary nature of MIR research and multi-faceted nature of human music perception make the sharing and reuse of techniques and implementations for particular facets of music perception and music information retrieval tasks highly desirable. In addition the field makes use of a diverse range of file formats, software environments and toolkits for extracting, encoding and accessing MIR data and services, making reuse extremely challenging. The NEMA project aims to provide the MIR field with a high quality, secure and extensible workflow environment to facilitate: computation over remote audio and resource collections; optimal code reuse, interoperability between data formats and types, sharing and dissemination; standardised, high-quality evaluation procedures; and the encoding of metadata, data and results in a format suitable for distributed systems.