liqingchunnnn / Only-Noisy-Training
A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy audio signals in audio space for the first time.
☆65Updated 2 years ago
Alternatives and similar repositories for Only-Noisy-Training:
Users that are interested in Only-Noisy-Training are comparing it to the libraries listed below
- Perceptual Contrast Stretching on Target Feature for Speech Enhancement (Accepted by INTERSPEECH 2022)☆58Updated 9 months ago
- A Diffusion Probabilistic Model for Target Sound Extraction☆36Updated 5 months ago
- Single channel speech source separation by diffusion process (ICASSP 2023)☆99Updated 11 months ago
- Unsupervised domain adaptation for conversational speech enhancement using RemixIT☆53Updated last year
- Nested U-Net with two-level skip connections for speech enhancement☆34Updated last year
- Phase-aware speech enchancement with Deep Complex U-Net☆104Updated last year
- A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Mult…☆34Updated 4 months ago
- DCCRN with various loss functions☆94Updated 2 years ago
- DNN-based SE in the frequency domain using Pytorch. You can test some state-of-the-art networks using T-F masking or spectral mapping met…☆53Updated 2 years ago
- ☆41Updated 9 months ago
- The implementation of "X-TF-GridNet: A Time-Frequency Domain Target Speaker Extraction Network with Adaptive Speaker Embedding Fusion", w…☆47Updated 4 months ago
- ☆69Updated 2 years ago
- Official code for MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enh…☆32Updated this week
- ☆23Updated last year
- A STFT/iSTFT written up in PyTorch using 1D Convolutions☆27Updated 7 months ago
- wsj0-{2, 3, 4, 5} mix generation scripts, in Python.☆55Updated 3 years ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆86Updated 6 months ago
- ☆109Updated 4 years ago
- ☆46Updated 5 months ago
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆46Updated last month
- Fully Quantized Neural Networks For Speech Enhancement☆61Updated last year
- This is the official implementation of the LiSenNet☆56Updated 3 months ago
- speech enhancement metrics：CSIG, CBAK, CMOS, SSNR, PESQ, STOI, ESTOI, SNR, IS, LLR, WSS☆63Updated last year
- A training code template for DNN-based speech enhancement.☆70Updated 3 weeks ago
- ☆98Updated last year
- This repository contains the audio samples for "D2Former: A Fully Complex Dual-Path Dual-Decoder Conformer Network using Joint Complex Ma…☆38Updated last year
- A fast implementation of bss_eval metrics for blind source separation☆134Updated 2 years ago
- Boosting Self-Supervised Embeddings for Speech Enhancement☆47Updated 2 years ago
- The official repo: "McNet: Fuse Multiple Cues for Multichannel Speech Enhancement", ICASSP 2023☆111Updated last year
- Keep track of good articles on speech processing, mainly on speech enhancement, include speech denoise, speech dereverberation and aec、ag…☆44Updated 7 months ago