DASEE A Synthetic Database of Domestic Acoustic Scenes and Events in Dementia Patients Environment

TL;DR

This paper introduces DASEE, a synthetic domestic audio database tailored for dementia patient environments, enabling improved sound scene analysis with a baseline model achieving high classification accuracy.

Contribution

The creation of a detailed, unbiased synthetic audio database reflecting real-world dementia environments, including noise and location information, for domestic audio classification research.

Findings

Database contains 11 classes of sound scenes and events.

Baseline model achieved an 86.24% weighted F1-score.

Includes both quiet and noisy environment recordings.

Abstract

Access to informative databases is a crucial part of notable research developments. In the field of domestic audio classification, there have been significant advances in recent years. Although several audio databases exist, these can be limited in terms of the amount of information they provide, such as the exact location of the sound sources, and the associated noise levels. In this work, we detail our approach on generating an unbiased synthetic domestic audio database, consisting of sound scenes and events, emulated in both quiet and noisy environments. Data is carefully curated such that it reflects issues commonly faced in a dementia patients environment, and recreate scenarios that could occur in real-world settings. Similarly, the room impulse response generated is based on a typical one-bedroom apartment at Hebrew SeniorLife Facility. As a result, we present an 11-class database containing excerpts of clean and noisy signals at 5-seconds duration each, uniformly sampled at 16 kHz. Using our baseline model using Continues Wavelet Transform Scalograms and AlexNet, this yielded a weighted F1-score of 86.24 percent.