DCASE 2018 Challenge - Task 5: Monitoring of domestic activities based on multi-channel acoustics

TL;DR

This paper describes Task 5 of the DCASE 2018 Challenge, focusing on using multi-channel acoustics to improve classification of domestic activities through spectral and spatial cues.

Contribution

It introduces a new dataset and baseline system for classifying domestic activities using multi-channel audio, emphasizing spectral and spatial feature extraction.

Findings

Multi-channel recordings improve activity classification accuracy.

Baseline neural network system provides a reference for future research.

Dataset derived from SINS database supports multi-microphone analysis.

Abstract

The DCASE 2018 Challenge consists of five tasks related to automatic classification and detection of sound events and scenes. This paper presents the setup of Task 5 which includes the description of the task, dataset and the baseline system. In this task, it is investigated to which extent multi-channel acoustic recordings are beneficial for the purpose of classifying domestic activities. The goal is to exploit spectral and spatial cues independent of sensor location using multi-channel audio. For this purpose we provided a development and evaluation dataset which are derivatives of the SINS database and contain domestic activities recorded by multiple microphone arrays. The baseline system, based on a Neural Network architecture using convolutional and dense layer(s), is intended to lower the hurdle to participate the challenge and to provide a reference performance.