Description and Discussion on DCASE 2025 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes

TL;DR

This paper introduces the DCASE 2025 Challenge Task 4 focused on spatial semantic segmentation of sound scenes, aiming to improve sound event detection and separation using multi-channel spatial audio data.

Contribution

It defines the S5 task for DCASE 2025, presents a new dataset, and reports initial experimental results, advancing research in spatial sound scene analysis.

Findings

Initial experimental results demonstrate the feasibility of the S5 approach.

The newly curated dataset supports development of spatial sound scene analysis.

The task sets a benchmark for future research in spatial semantic segmentation.

Abstract

Spatial Semantic Segmentation of Sound Scenes (S5) aims to enhance technologies for sound event detection and separation from multi-channel input signals that mix multiple sound events with spatial information. This is a fundamental basis of immersive communication. The ultimate goal is to separate sound event signals with 6 Degrees of Freedom (6DoF) information into dry sound object signals and metadata about the object type (sound event class) and representing spatial information, including direction. However, because several existing challenge tasks already provide some of the subset functions, this task for this year focuses on detecting and separating sound events from multi-channel spatial input signals. This paper outlines the S5 task setting of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge Task 4 and the DCASE2025 Task 4 Dataset, newly recorded and curated for this task. We also report experimental results for an S5 system trained and evaluated on this dataset. The full version of this paper will be published after the challenge results are made public.