TAU Spatial Sound Events 2019 - Ambisonic and Microphone Array, Evaluation Datasets

This package consists of two evaluation datasets, TAU Spatial Sound Events 2019 - Ambisonic and TAU Spatial Sound Events 2019 - Microphone Array. These datasets contain recordings from an identical scene, with TAU Spatial Sound Events 2019 - Ambisonic providing four-channel First-Order Ambisonic (FOA) recordings while TAU Spatial Sound Events 2019 - Microphone Array provides four-channel directional microphone recordings from a tetrahedral array configuration. Both formats are extracted from the same microphone array. The recordings in the two datasets consist of stationary point sources from multiple sound classes each associated with a temporal onset and offset time, and DOA coordinate represented using azimuth and elevation angle. These evaluation datasets are part of the DCASE 2019 Sound Event Localization and Detection Task. The corresponding development datasets can be downloaded here.

The IRs were collected in Finland by Tampere University between 12/2017 - 06/2018. The data collection received funding from the European Research Council, grant agreement 637422 EVERYSOUND.

• The foa_eval.zip, correspond to audio data of TAU Spatial Sound Events 2019 - Ambisonic evaluation dataset.
• The mic_eval.zip, correspond to audio data of TAU Spatial Sound Events 2019 - Microphone Array evaluation dataset.

-- Version 2 updates --

The DCASE 2019 sound event localization and detection task has now ended. Hence we are releasing the reference labels for the evaluation dataset in this version.

• The metadata_eval.zip is the common metadata for both TAU Spatial Sound Events 2019 - Ambisonic and TAU Spatial Sound Events 2019 - Microphone Array evaluation datasets.   
• The short2longnames.txt file consists of the corresponding names for each recording in the dataset in the development-set format, i.e., including the information of the impulse response location and the maximum number of overlapping sound events in the recording.

Download the zip files corresponding to the dataset of interest and use your favorite compression tool to unzip these split zip files.