STARSS22

Sony-TAu Realistic Spatial Soundscapes 2022

Dataset Information
Modalities
Audio
Introduced
2022
License
MIT license
Homepage
Official Website
Contents

Overview

The Sony-TAu Realistic Spatial Soundscapes 2022(STARSS22) dataset consists of recordings of real scenes captured with high channel-count spherical microphone array (SMA). The recordings are conducted from two different teams at two different sites, Tampere University in Tammere, Finland, and Sony facilities in Tokyo, Japan. Recordings at both sites share the same capturing and annotation process, and a similar organization. They are organized in sessions, corresponding to distinct rooms, human participants, and sound making props with a few exceptions.

Source: STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events

Image https://arxiv.org/pdf/2206.01948v2.pdf

Variants: STARSS22

Associated Benchmarks

This dataset is used in 1 benchmark:

  • Sound Event Localization and Detection - Metrics: Class-dependent localization error, Class-dependent localization recall, location-dependent F1-score (macro), location-dependent F1-score (micro), Localization-dependent error rate (20°)

Recent Benchmark Submissions

Task Model Paper Date
Sound Event Localization and Detection Baseline (FOA) STARSS22: A dataset of spatial … 2022-06-04
Sound Event Localization and Detection Baseline (MIC) STARSS22: A dataset of spatial … 2022-06-04

Research Papers

Recent papers with results on this dataset:

External Links: