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.

本套件包含两个评测数据集，分别为TAU Spatial Sound Events 2019 - Ambisonic与TAU Spatial Sound Events 2019 - Microphone Array。两个数据集均基于同一场景录制：TAU Spatial Sound Events 2019 - Ambisonic提供四声道一阶Ambisonic（First-Order Ambisonic, FOA）音频，TAU Spatial Sound Events 2019 - Microphone Array则采用四面体阵列配置的四声道指向性麦克风录制音频，两种格式均源自同一麦克风阵列。

两个数据集的录制内容均包含多个类别的静止点声源，每个声源均配有对应的时间起始与终止时刻，以及以方位角与仰角表征的到达方向（Direction of Arrival, DOA）坐标。本评测数据集属于DCASE 2019声音事件定位与检测任务（DCASE 2019 Sound Event Localization and Detection Task），对应开发数据集可在此处下载。

本数据集所用的脉冲响应（Impulse Response, IR）于2017年12月至2018年6月间由芬兰坦佩雷大学采集，该数据采集项目获得欧洲研究委员会（European Research Council）资助，资助协议编号为637422 EVERYSOUND。

`foa_eval.zip` 对应TAU Spatial Sound Events 2019 - Ambisonic评测数据集的音频数据；`mic_eval.zip` 对应TAU Spatial Sound Events 2019 - Microphone Array评测数据集的音频数据。

-- 版本2更新说明 --
DCASE 2019声音事件定位与检测任务现已结束，因此本版本将发布评测数据集的参考标签。

`metadata_eval.zip` 为上述两个评测数据集的通用元数据文件。`short2longnames.txt` 文件包含开发集格式下各条录音的对应名称，其中涵盖了该录音对应的脉冲响应位置以及录音中最大重叠声音事件数量的信息。

请下载目标数据集对应的压缩包，并使用您偏好的解压工具对这些分卷压缩包进行解压。