Description and Discussion on DCASE 2026 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes

TL;DR

This paper overviews the DCASE 2026 Challenge Task 4, focusing on spatial semantic segmentation of sound scenes, including task updates, evaluation metrics, datasets, and analysis of submitted systems.

Contribution

It introduces key updates to the S5 task for DCASE 2026, including handling multiple sources of the same class and no target sources, with new evaluation metrics and datasets.

Findings

Experimental results of submitted systems are reported and analyzed.

Task updates better reflect real-world acoustic scene conditions.

Abstract

This paper presents an overview of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2026 Challenge Task 4, Spatial Semantic Segmentation of Sound Scenes (S5). The S5 task focuses on the joint detection and separation of sound events in complex spatial audio mixtures, contributing to the foundation of immersive communication. First introduced in DCASE 2025, the S5 task continues in DCASE 2026 Task 4 with key changes to better reflect real-world conditions, including allowing mixtures to contain multiple sources of the same class and to contain no target sources. In this paper, we describe task setting, along with the corresponding updates to the evaluation metrics and dataset. The experimental results of the submitted systems are also reported and analyzed. The official access point for data and code is https://github.com/nttcslab/dcase2026_task4_baseline.