Through the XBAT project we extend MATLAB to facilitate computer-assisted sound analysis and annotation. XBAT allows you to scan arbitrarily long recordings using automated recognition techniques and to interactively review, amend, and expand automated annotation. Through an extensible architecture XBAT facilitates the integration new algorithms and reuse of community contributions.
The design of XBAT models typical stages in the sound analysis workflow. The extensible architecture allows the basic components to be interchanged and share a common infrastructure.
Users can access and visualize sounds, browse and search for salient events, and annotate and measure events. Developers can quickly create easy-to-use extensions with a powerful plug-in architecture.
XBAT has been developed in collaboration with conservation scientists and animal communication researchers at the Bioacoustics Research Program of the Cornell Laboratory of Ornithology.
It was designed to satisfy the diverse sound analysis needs of scientists who deal with large-scale data sets from both marine and terrestrial environments.