Author

Haohe Liu

h-index 27 View on Semantic Scholar

We have 1 of 68 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

FlowSep 2: Self-Supervised Flow Matching for Language-Queried Audio Source Separation

This work proposes FlowSep2, a text-conditioned flow-matching generative model for LASS, which learns to generate the target source representation from Gaussian noise in a latent space, conditioned on both the mixture representation and the text query.

Yiitan Yuan, Xubo Liu, Haohe Liu et al. · 0 citations