NTIA / WEnets
Reference Implementations of Waveform Evaluation Networks (WEnets)
☆23Updated last year
Related projects ⓘ
Alternatives and complementary repositories for WEnets
- Support for Clarity Enhancement and Prediction Challenges (obsolete - see README)☆46Updated 2 years ago
- speech enhancement metrics:CSIG, CBAK, CMOS, SSNR, PESQ, STOI, ESTOI, SNR, IS, LLR, WSS☆59Updated last year
- ☆48Updated 5 months ago
- A fast implementation of bss_eval metrics for blind source separation☆131Updated 2 years ago
- ☆33Updated 2 years ago
- STOI loss function in PyTorch☆87Updated last month
- ☆48Updated 9 months ago
- ☆48Updated 2 years ago
- Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation☆95Updated 2 years ago
- ☆75Updated 5 months ago
- audio source separation evaluation metrics☆27Updated 5 years ago
- ☆52Updated 2 years ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆57Updated 2 months ago
- Deep Learning Based Monaural Speech Dereverberation Models: Hope We Can Get Better Performance of Dereverberation☆15Updated 2 years ago
- Pytorch implementation of subband decomposition☆89Updated 2 years ago
- ☆20Updated 3 years ago
- Multi-Phase Gammatone Filterbank (MP-GTF) construction for Python☆46Updated 4 years ago
- Python implementation of the SRMR toolbox☆113Updated 4 months ago
- Causality Check in Frame-online Speech Separation☆43Updated last year
- Speech Enhancement Metrics (PESQ, CSIG, CBAK, COVL)☆63Updated 4 years ago
- Python loaders for many Real Room Impulse Response databases☆85Updated last month
- Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge in Online Conferencing Applications☆42Updated 2 years ago
- Augmenting Room Impulse Response☆37Updated last year
- Unofficial Pytorch Lightning Implementation of "Real-time Speech Frequency Bandwidth Extension"☆27Updated last year
- ☆174Updated 11 months ago
- Beam-guided TasNet☆46Updated 2 years ago
- ☆22Updated 2 years ago
- Boosting Self-Supervised Embeddings for Speech Enhancement☆44Updated 2 years ago
- NOMAD: Non-Matching Audio Distance (ICASSP 2024)☆24Updated 3 weeks ago
- ☆67Updated 2 years ago