WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection

Abstract

This work aims to advance sound event detection (SED) research by presenting a new large language model (LLM)-powered dataset namely wild domestic environment sound event detection (WildDESED). It is crafted as an extension to the original DESED dataset to reflect diverse acoustic variability and complex noises in home settings. We leveraged LLMs to generate eight different domestic scenarios based on target sound categories of the DESED dataset. Then we enriched the scenarios with a carefully tailored mixture of noises selected from AudioSet and ensured no overlap with target sound. We consider widely popular convolutional neural recurrent network to study WildDESED dataset, which depicts its challenging nature. We then apply curriculum learning by gradually increasing noise complexity to enhance the model’s generalization capabilities across various noise levels. Our results with this approach show improvements within the noisy environment, validating the effectiveness on the WildDESED dataset promoting noise-robust SED advancements.

Method

What type of background noises do we use?

What are the domestic scenarios we choose?

Example diagrams of Scenarios

Example Clips

Scenarios

Noisy Clips

Original Clips

Morning

Pet Care

Bathroom

Emergency

BibTeX

@inproceedings{Xiao2024WildDESED,
  title={{WildDESED}: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System},
  author={Yang Xiao and Rohan Kumar Das},
  booktitle={Proceedings of the Detection and Classification of Acoustic Scenes and Events 2024 Workshop (DCASE2024)},
  pages = {196--200},
  year={2024},
}