SungFeng-Huang / SSL-pretraining-separationLinks
Official repository of our paper: https://arxiv.org/abs/2010.15366
☆63Updated 4 years ago
Alternatives and similar repositories for SSL-pretraining-separation
Users that are interested in SSL-pretraining-separation are comparing it to the libraries listed below
Sorting:
- Code for the ICASSP-2021 paper: Continuous Speech Separation with Conformer.☆119Updated 2 years ago
- ☆126Updated 4 years ago
- SpEx+(tied) source code☆88Updated 2 years ago
- ☆52Updated 3 years ago
- ☆113Updated 4 years ago
- Conferencing Speech Challenge☆95Updated 4 years ago
- The implementation of "Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement"☆122Updated 3 years ago
- Libri-CSS: dataset and evaluation pipeline☆148Updated 2 years ago
- A simple package for Guided source separation (GSS)☆128Updated last year
- A personal toolkit for single/multi-channel speech recognition & enhancement & separation.☆145Updated 2 years ago
- wsj0-{2, 3, 4, 5} mix generation scripts, in Python.☆69Updated 4 years ago
- ☆37Updated 4 years ago
- DCCRN with various loss functions☆102Updated 3 years ago
- STOI loss function in PyTorch☆99Updated last year
- Boosting Self-Supervised Embeddings for Speech Enhancement☆47Updated 3 years ago
- Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancement☆81Updated 4 years ago
- Speech Enhancement Metrics (PESQ, CSIG, CBAK, COVL)☆75Updated 5 years ago
- Speech enhancement system for the CHiME-5 dinner party scenario☆109Updated 8 months ago
- implementation of "DCCRN-Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement" by pytorch☆55Updated 4 years ago
- The code for the Interspeech paper "Speaker Embedding Extraction with Phonetic Information"☆45Updated 6 years ago
- Speech Separation☆76Updated last year
- The official repo: "McNet: Fuse Multiple Cues for Multichannel Speech Enhancement", ICASSP 2023☆123Updated 2 years ago
- ☆51Updated 4 years ago
- Multi-Task Audio Source Separation, Two-Stage Model, Complex Domain.☆93Updated 2 years ago
- Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation☆113Updated 3 years ago
- This repository contains a set of codes to run (i.e., train, perform inference with, evaluate) a diarization method called EEND-vector-cl…☆76Updated 3 years ago
- multi-scale time domain speaker extraction☆65Updated 4 years ago
- ☆201Updated last year
- transformer based neural network for speech enhancement in time domain☆74Updated 3 years ago
- Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge in Online Conferencing Applications☆46Updated 3 years ago