SLoClas: A Database for Joint Sound Localization and Classification

TL;DR

This paper introduces SLoClas, a comprehensive database for sound localization and classification, along with a baseline neural network, achieving high accuracy and supporting noise robustness studies.

Contribution

The paper presents a new publicly available database and a baseline method for joint sound localization and classification research.

Findings

Achieved 95.21% localization accuracy.

Achieved 80.01% classification accuracy.

Provided a publicly available dataset and source code.

Abstract

In this work, 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 Sound Localization and Classification Network (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.