We present the development of a new database, namely Sound Localization and Classification (SLoClas) corpus, for studying and analyzing sound localization and classification. The corpus contains a total of 23.27 hours of data recorded using a 4-channel microphone array. 10 classes of sounds are played over a loudspeaker at 1.5 meters distance from the array by varying the Direction of Arrival (DoA) from 1 degree to 360 degree at an interval of 5 degree. To facilitate the study of noise robustness, 6 types of outdoor noise are recorded at 4 DoAs, using the same devices. Moreover, we propose a baseline method, namely SLCnet and present the experimental results and analysis conducted on the collected SLoClas database. We achieve the accuracy of 95.21% and 80.01% for sound localization and classification, respectively. We publicly release this database and the source code for research purpose. We release this database to the public for research activities.
Link to Download the database:
Link to Download the code:
Applications
- Joint framework for sound localization and sound event classification
Reference
Please refer the following paper if you use this database
Xinyuan Qian and Bidisha Sharma and Amine El Abridi and Haizhou Li, "SLoClas: A Database for Joiunt Sound Localization and Classification." arXiv preprint arXiv: 2108.02539v1 (2021). https://arxiv.org/abs/2108.02539
@misc{qian2021sloclas, title={SLoClas: A Database for Joint Sound Localization and Classification}, author={Xinyuan Qian and Bidisha Sharma and Amine El Abridi and Haizhou Li}, year={2021}, eprint={2108.02539}, archivePrefix={arXiv}, primaryClass={cs.SD} }
Recording setup for SLoClas database
Details of the SLoClas database
The proposed SLCnet architecture
