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

05/06/2021
by   Jakob Abeßer, et al.
0

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.

READ FULL TEXT
research
03/23/2021

GISE-51: A scalable isolated sound events dataset

Most of the existing isolated sound event datasets comprise a small numb...
research
04/23/2019

Towards joint sound scene and polyphonic sound event recognition

Acoustic Scene Classification (ASC) and Sound Event Detection (SED) are ...
research
11/03/2021

A Strongly-Labelled Polyphonic Dataset of Urban Sounds with Spatiotemporal Context

This paper introduces SINGA:PURA, a strongly labelled polyphonic urban s...
research
05/21/2019

A multi-room reverberant dataset for sound event localization and detection

This paper presents the sound event localization and detection (SELD) ta...
research
12/19/2021

Detect what you want: Target Sound Detection

Human beings can perceive a target sound that we are interested in from ...
research
10/19/2020

BIRD: Big Impulse Response Dataset

This paper introduces BIRD, the Big Impulse Response Dataset. This open ...
research
07/08/2020

Training Sound Event Detection On A Heterogeneous Dataset

Training a sound event detection algorithm on a heterogeneous dataset in...

Please sign up or login with your details

Forgot password? Click here to reset