Uses same clean speech as VoiceBank+Demand but more noise types. Features much lower SNRs ([−10, −5, 0, 5, 10, 15, 20] dB) compared to VoiceBank+Demand and has babble and speech shaped noise in both train, validation, and test set.
Variants: VB-DemandEx
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Speech Enhancement | MambAttention | MambAttention: Mamba with Multi-Head Attention … | 2025-07-01 |
| Speech Enhancement | SEMamba | MambAttention: Mamba with Multi-Head Attention … | 2025-07-01 |
| Speech Enhancement | xLSTM-SENet | MambAttention: Mamba with Multi-Head Attention … | 2025-07-01 |
| Speech Enhancement | MP-SENet | MambAttention: Mamba with Multi-Head Attention … | 2025-07-01 |
Recent papers with results on this dataset: