ASSDMay 6, 2021

USM-SED - A Dataset for Polyphonic Sound Event Detection in Urban Sound Monitoring Scenarios

arXiv:2105.02592v110 citations
Originality Synthesis-oriented
AI Analysis

This provides a resource for researchers in audio processing and urban monitoring, but it is incremental as it builds on existing datasets like FSD50k.

The paper tackles the problem of polyphonic sound event detection in urban environments by introducing a new synthesized dataset, USM-SED, which includes 20,000 soundscapes created from isolated sounds with varied stereo positioning and loudness levels.

This paper introduces a novel dataset for polyphonic sound event detection in urban sound monitoring use-cases. Based on isolated sounds taken from the FSD50k dataset, 20,000 polyphonic soundscapes are synthesized with sounds being randomly positioned in the stereo panorama using different loudness levels. The paper gives a detailed discussion of possible application scenarios, explains the dataset generation process in detail, and discusses current limitations of the proposed USM-SED dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes