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

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

4 Jul 2024arXiv:2407.03656archive 2025-07-28

Yang Xiao, Rohan Kumar Das

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.

PaperPDFCode

Code

swagshaw/wilddesed officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Event DetectionLanguage ModelingLanguage ModellingLarge Language ModelSound Event Detection

Datasets

Introduced by this paper, per the archive.

WildDESED

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sound Event Detection WildDESED CRNN (WildDESED + Curriculrm learning) PSDS1 (-5dB) 0.049 #3 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED + Curriculrm learning) PSDS1 (0dB) 0.114 #3 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED + Curriculrm learning) PSDS1 (10dB) 0.212 #3 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED + Curriculrm learning) PSDS1 (5dB) 0.175 #3 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED + Curriculrm learning) PSDS1 (Clean) 0.265 #3 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED) PSDS1 (-5dB) 0.048 #4 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED) PSDS1 (0dB) 0.087 #4 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED) PSDS1 (10dB) 0.175 #4 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED) PSDS1 (5dB) 0.135 #4 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN (WildDESED) PSDS1 (Clean) 0.200 #4 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN PSDS1 (-5dB) 0.017 #5 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN PSDS1 (0dB) 0.064 #5 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN PSDS1 (10dB) 0.222 #5 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN PSDS1 (5dB) 0.148 #5 of 5 Archive leaderboard report
Sound Event Detection WildDESED CRNN PSDS1 (Clean) 0.348 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections