Pinned Repositories
aasist
Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"
AI-interview-cards
最完整的AI算法面试题目仓库，1000道，25个类目
awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
cv_note
记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/
data
GAIN
Code of the system developed by the USTC-NELSLIP team for SemEval-2022 Task 11 MultiCoNER.
PercepNet
(Under construct) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
sgmse
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
speaker-embedding-with-phonetic-information
The code for the Interspeech paper "Speaker Embedding Extraction with Phonetic Information"
voxceleb_trainer
In defence of metric learning for speaker recognition
qijiajun's Repositories
qijiajun/aasist
Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"
qijiajun/AI-interview-cards
最完整的AI算法面试题目仓库，1000道，25个类目
qijiajun/awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
qijiajun/cv_note
记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/
qijiajun/data
qijiajun/GAIN
Code of the system developed by the USTC-NELSLIP team for SemEval-2022 Task 11 MultiCoNER.
qijiajun/PercepNet
(Under construct) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
qijiajun/sgmse
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
qijiajun/speaker-embedding-with-phonetic-information
The code for the Interspeech paper "Speaker Embedding Extraction with Phonetic Information"
qijiajun/voxceleb_trainer
In defence of metric learning for speaker recognition