Speech & Audio AI

A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation

KKai LiJJintao ChengCChang ZengZZijun YanHHelin WangZZixiong SuBBo ZhengXXiaolin Hu
Published
January 30, 2026
Authors
8

Abstract

Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods continue to suffer from residual interference in complex acoustic scenes. This performance limitation stems largely from a data bottleneck: in-the-wild datasets contain weak labels and severe co-occurrence of events. These flaws induce models to learn spurious correlations between background noise and target categories instead of robust acoustic features. To address this, we propose an automated pipeline that eliminates co-occurrence of events by mining high-purity single-event segments from in-the-wild datasets via a semantically consistent synthesis protocol. Utilizing this pipeline, we constructed Hive, a high-quality synthetic dataset comprising 2.4k hours of raw audio. Experimental results demonstrate that, compared with the state-of-the-art model SAM-Audio which was trained on a huge dataset sim500 times larger than Hive, certain open-source models trained on Hive achieve competitive separation accuracy and perceptual quality. Moreover, these models exhibited remarkable zero-shot generalization on out-of-distribution evaluation benchmarks. These findings highlight that prioritizing purity of supervised signals enables significant data efficiency, offering a new paradigm for training robust auditory foundation models with reduced computational costs. Code and dataset are available at https://shandaai.github.io/Hive.

Keywords

universal sound separationin-the-wild datasetsco-occurrence of eventssemantically consistent synthesis protocolhigh-purity single-event segmentsHive datasetSAM-Audiozero-shot generalizationauditory foundation modelsdata efficiency

More in Speech & Audio AI

View all
A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation | Paperchime