Meyda: an Audio Feature Extraction Library for the Web Audio API

There are many existing native libraries and frameworks for audio feature extraction used in multimedia information retrieval. Many are dependent on highly optimised low level code to cope with the high performance requirements of realtime audio analysis. In this paper, we present a new audio feature extractor library, Meyda1 , for use with the JavaScript Web Audio API, and detail its benchmarking results. Meyda provides the first library for audio feature extraction in the web client, which will enable music information retrieval systems, complex visualisations and a wide variety of technologies and creative projects that previously were relegated to native software. The Meyda project, including source code and documentation is released under an MIT license.