nanless / universal-speech-enhancement
Apply Score diffusion to improve speech signals recorded under various adverse conditions and distortions, including noise, reverberation, clipping, equalization (EQ) distortion, packet loss, codec loss, bandwidth limitations, and other forms of degradation.
☆59Updated 8 months ago
Alternatives and similar repositories for universal-speech-enhancement:
Users that are interested in universal-speech-enhancement are comparing it to the libraries listed below
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆45Updated last week
- ☆45Updated 6 months ago
- ☆48Updated 2 years ago
- ☆65Updated last year
- Official Implementation of TSELM: Target speaker extraction using discrete tokens and language models☆42Updated 3 months ago
- Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enha…☆33Updated 7 months ago
- The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.☆95Updated last year
- Production first, nn-based on-device signal processing toolkit.☆64Updated last year
- [Interspeech 2024] Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement☆37Updated 4 months ago
- This is the official implementation of the LiSenNet☆69Updated 4 months ago
- Fully Quantized Neural Networks For Speech Enhancement☆61Updated last year
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆47Updated 2 months ago
- ☆42Updated 11 months ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆68Updated 7 months ago
- This is official repository of new SOTA diffusion models based method for speech enhancement☆38Updated 8 months ago
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆65Updated 3 weeks ago
- ☆47Updated this week
- ☆26Updated last year
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆91Updated 7 months ago
- Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction☆37Updated 4 months ago
- Official code for MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enh…☆36Updated 3 weeks ago
- The official repo of UL-UNAS, an ultra-lightweight SE model.☆31Updated 3 weeks ago
- ICASSP2025Dynamic Embedding Causal Target Speech Extraction☆2Updated 2 weeks ago
- faster inference☆27Updated 2 months ago
- Official repo of ICASSP 2024 paper - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.☆52Updated 2 months ago
- VOICOR: A Residual Iterative Voice Correction Framework for Monaural Speech Enhancement☆39Updated 6 months ago
- The implementation of TaylorBeamformer, which is in submission to Interspeech2022☆40Updated 2 years ago
- real-time speech enhance☆14Updated last year
- ☆13Updated 5 months ago
- Official repository for Mamba-based Segmentation Model for Speaker Diarization☆34Updated 5 months ago