Task-aware Unified Source Separation - Audio Examples

This page provides several audio examples of the Task-aware Unified Source Separation (TUSS) model.
As shown in Fig.1, the model features learnable prompts to specify what source to separate and changes its behavior based on the prompts.
The audio examples include both synthetic mixtures and real recordings.


Audio examples

We provide the audio examples of the following configurations (for some tasks, we skip the specialist model).
We utilized the medium model and M* corresponds to the ID in Table III of the paper.

Example 1 on DnR dataset

▼ Click to expand

Example 2 on DnR dataset

▼ Click to expand

Example on FMA dataset

▼ Click to expand

Example on WHAM! noise (Speech + SFX)

▼ Click to expand

Example on WHAM! noise (Drums + SFX)

▼ Click to expand