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

TL;DR

This paper introduces WildDESED, a new LLM-powered dataset for sound event detection in complex domestic environments, and demonstrates its effectiveness for training noise-robust models.

Contribution

The creation of WildDESED, an extended dataset with diverse domestic noise scenarios generated using LLMs, and the application of curriculum learning to improve noise robustness.

Findings

Improved sound event detection accuracy in noisy environments.

Demonstrated the effectiveness of curriculum learning for noise robustness.

Validated the dataset's challenging nature through CNN-RNN experiments.

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.