Pinned Repositories
16k_SE_codes
24k_SE
24k speech enhancement
audio-dataset
This repository contains the dataset required for domain adaptive speech enhancement tasks. Clean utterances and noises are provided directly. Noisy utterances can be generated following the corresponding text files.
DNS-Challenge
This repo contains the scripts, models and required files for the Interspeech 2020 Deep Noise Suppression (DNS) Challenge. We are open sourcing clean speech and noise files as well. Participants of this challenge will use the scripts from this repo to create data to train their noise suppressors. They will compare their method with our baseline noise suppressor and report the results.
FTCRN-based-Metric-GAN-for-Hearing-Aids
This repository provides the network codes, FIG6 codes and the test set of the manuscript "Speech Denoising and Compensation for Hearing Aids using an FTCRN-based Metric GAN".
UCLFWPKD-for-SE
This is the repository of the manuscript "Residual Fusion Probabilistic Knowledge Distillation for Speech Enhancement".
JMCheng-SEU's Repositories
JMCheng-SEU/FTCRN-based-Metric-GAN-for-Hearing-Aids
This repository provides the network codes, FIG6 codes and the test set of the manuscript "Speech Denoising and Compensation for Hearing Aids using an FTCRN-based Metric GAN".
JMCheng-SEU/UCLFWPKD-for-SE
This is the repository of the manuscript "Residual Fusion Probabilistic Knowledge Distillation for Speech Enhancement".
JMCheng-SEU/24k_SE
24k speech enhancement
JMCheng-SEU/16k_SE_codes
JMCheng-SEU/audio-dataset
This repository contains the dataset required for domain adaptive speech enhancement tasks. Clean utterances and noises are provided directly. Noisy utterances can be generated following the corresponding text files.
JMCheng-SEU/DNS-Challenge
This repo contains the scripts, models and required files for the Interspeech 2020 Deep Noise Suppression (DNS) Challenge. We are open sourcing clean speech and noise files as well. Participants of this challenge will use the scripts from this repo to create data to train their noise suppressors. They will compare their method with our baseline noise suppressor and report the results.