This dataset provides the ground truth data for the DCASE2025Task4EvaluationDataset. It contains the ground truth separation sounds for the target sound events in the 2290 mixtures of evaluation set. This dataset is intended to be used in conjunction with the following datasets and the script: Training and validation data: DCASE2025Task4Dataset: The Dataset for Spatial Semantic Segmentation of Sound Scenes Evaluation data: DCASE2025Task4EvaluationDataset : The Evaluation Dataset for Spatial Semantic Segmentation of Sound Scenes Script for evaluation: nttrd-cslabs/dcase2025_SpatialSemanticSegmentation_evaluator Other resources: Description page of DCASE2025 task4: Spatial Semantic Segmentation of Sound Scenes - DCASE Baseline System Github page: nttcslab/dcase2025_task4_baseline arXiv paper describing this dataset: [2506.10676] Description and Discussion on DCASE 2025 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes