Stars
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
The official pytorch implemention of the Intespeech 2024 paper "Reshape Dimensions Network for Speaker Recognition"
Speaker verification using ResnetSE (EER=0.0093) and ECAPA-TDNN
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Noise supression using deep filtering
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
转换网易云音乐 ncm 到 mp3 / flac. Convert Netease Cloud Music ncm files to mp3/flac files.
Algorithm for blind estimation of reverberation time
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
语音算法相关资源汇总 Resource for Speech Processing || NEWS: official link of VoxCeleb fails recently and an external link is added for download
Robust Speech Recognition via Large-Scale Weak Supervision
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…
Keyword spotting, Speech wake_up, by pytorch, DNN, CNN, TDNN, DFSMN, LSTM
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
VS Code extension that allows you to preview and play audio files.
A small package to create visualizations of PyTorch execution graphs
Automatic headphone equalization from frequency responses
rishikksh20 / multiband-hifigan
Forked from jik876/hifi-ganHiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Dataset and baseline code for the VocalSound dataset (ICASSP2022).
Pytorch implementation of subband decomposition
Frontend filterbank learning module with HVQT initialization capabilities.
Main codebase for TeXworks, a simple interface for working with TeX documents
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.