Audio Tree Reconstruction Error benchmark — 10,000 synthetic audio scenes
for evaluating whether audio encoders represent multi-source scenes compositionally.
Companion dataset to the ICASSP 2026 paper Evaluating Compositional Structure in Audio
Representations. See also the
zero-shot benchmark chuyangchenn/a-coat-2k.
ds = load_dataset("chuyangchenn/a-tre-10k", split="train") # or "val", "test"
ex = ds[0]… See the full description on the dataset page:
https://huggingface.co/datasets/chuyangchenn/a-tre-10k.
