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

2018/07/30 by Dekkers, Gert, Vuegen, Lode, van Waterschoot, Toon +2
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1807.11246

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.

Related

• DCASE 2018 Challenge: Solution for Task 5
• Cross-task learning for audio tagging, sound event detection spatial localization: DCASE 2019 baseline systems
• Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems
• Domestic Activities Classification from Audio Recordings Using Multi-scale Dilated Depthwise Separable Convolutional Network
• SAM-GCNN: A Gated Convolutional Neural Network with Segment-Level Attention Mechanism for Home Activity Monitoring