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