line / open-universeLinks
Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.
☆101Updated 11 months ago
Alternatives and similar repositories for open-universe
Users that are interested in open-universe are comparing it to the libraries listed below
Sorting:
- SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)☆78Updated this week
- Official data preparation scripts for the URGENT 2024 Challenge☆82Updated 2 months ago
- Expressive Anechoic Recordings of Speech (EARS)☆181Updated last year
- This is official repository of new SOTA diffusion models based method for speech enhancement☆42Updated last year
- Transformer with Local Modeling by Convolution for Speech Separation and Enhancement☆89Updated 2 months ago
- ☆49Updated 10 months ago
- ☆65Updated 2 years ago
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆68Updated this week
- Apply Score diffusion to improve speech signals recorded under various adverse conditions and distortions, including noise, reverberation…☆63Updated last year
- ☆87Updated 10 months ago
- Single channel speech source separation by diffusion process (ICASSP 2023)☆110Updated last year
- Speech Human Evaluation Estimation Toolkit (SHEET)☆93Updated 2 months ago
- The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.☆96Updated 2 years ago
- ☆176Updated 8 months ago
- Generation scripts for EARS-WHAM and EARS-Reverb☆35Updated last month
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆69Updated 11 months ago
- Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint☆70Updated 2 years ago
- TODO☆41Updated last year
- Official implementation for FlowSep☆58Updated 7 months ago
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆157Updated 3 years ago
- ☆28Updated last year
- BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models☆54Updated 9 months ago
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆79Updated 4 months ago
- Repo for source code of EBEN: Extreme Bandwidth Extension Network☆75Updated 2 months ago
- Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction☆40Updated 8 months ago
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆62Updated 2 months ago
- NOMAD: Non-Matching Audio Distance (ICASSP 2024)☆28Updated last month
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆74Updated 6 months ago
- PAM is a no-reference audio quality metric for audio generation tasks☆69Updated last year
- Official implementation of DNSMOS Pro (accepted at INTERSPEECH 2024).☆44Updated last month