CoolFace
Apppublic

RobinsAIWorld/unise-speech-enhancement

sourceHugging Faceupdated 2mo agoView on Hugging Face
1likes
App README

UniSE: Unified Speech Enhancement

This Space runs the UniSE model from the paper "UniSE: A Unified Framework for Decoder-only Autoregressive LM-Based Speech Enhancement" (arXiv:2510.20441).

Supported Tasks

  • —Speech Enhancement (SE): General-purpose denoising and clarity improvement (noise, reverb, packet loss).
  • —Target Speaker Extraction (TSE): Extract a target speaker from a mixture using reference enrollment audio.
  • —Speech Separation (SS): Separate mixed speakers into individual streams.

How it works

  1. 1.Extract hidden states from WavLM layers and obtain a unified representation by averaging across layers.
  2. 2.Use the decoder-only autoregressive language model to predict speech tokens autoregressively.
  3. 3.Decode the tokens into audio using the BiCodec neural audio codec.

References