audiolabs / torch-pesq
PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio
☆176Updated last year
Alternatives and similar repositories for torch-pesq:
Users that are interested in torch-pesq are comparing it to the libraries listed below
- ☆188Updated last year
- A fast implementation of bss_eval metrics for blind source separation☆135Updated 2 years ago
- Speech Enhancement Metrics (PESQ, CSIG, CBAK, COVL)☆70Updated 4 years ago
- Official data preparation scripts for the URGENT 2024 Challenge☆75Updated 2 months ago
- This is the official implementation of the SEMamba paper. (Accepted to IEEE SLT 2024)☆181Updated 2 months ago
- ☆98Updated last year
- StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation☆209Updated 6 months ago
- Blind source separation with independent vector analysis family of algorithm in torch☆96Updated 2 years ago
- Single channel speech source separation by diffusion process (ICASSP 2023)☆99Updated 11 months ago
- Libri-CSS: dataset and evaluation pipeline☆143Updated 2 years ago
- A simple package for Guided source separation (GSS)☆117Updated 9 months ago
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆155Updated 2 years ago
- Pytorch implementation of subband decomposition☆92Updated 2 years ago
- ☆91Updated last year
- ☆114Updated 3 years ago
- ☆78Updated 2 years ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆91Updated 6 months ago
- Evaluation and Benchmarking of Speech Super-resolution Methods☆148Updated 2 years ago
- MANNER: Multi-view Attention Network for Noise ERasure (Speech enhancement in time-domain)☆60Updated 2 years ago
- Machine and Deep Learning models for speech dereverberation☆109Updated 3 years ago
- wsj0-{2, 3, 4, 5} mix generation scripts, in Python.☆55Updated 3 years ago
- UT-Sarulab MOS prediction system using SSL models☆216Updated 11 months ago
- STOI loss function in PyTorch☆91Updated 5 months ago
- ☆92Updated 3 years ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆68Updated 6 months ago
- The implementation of "Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement"☆116Updated 2 years ago
- Expressive Anechoic Recordings of Speech (EARS)☆151Updated 8 months ago
- ☆64Updated last year
- Python implementation of the SRMR toolbox☆121Updated 8 months ago
- Room impulse response simulator using python☆95Updated 4 years ago