liu shuanghong's repositories
Loss-Gated-Learning
ICASSP 2022: 'Self-supervised Speaker Recognition with Loss-gated Learning'
TS-TalkNet
INTERSPEECH2023: Target Active Speaker Detection with Audio-visual Cues
Agglomerative-Hierarchical-Clustering-from-scratch
Build Agglomerative hierarchical clustering algorithm from scratch, i.e. WITHOUT any advance libraries such as Numpy, Pandas, Scikit-learn, etc.
openTSNE
Extensible, parallel implementations of t-SNE
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
SV_eval_protocols_for_SD
Speaker verification evaluation protocols simulating speaker diarisation
D-TDNN
PyTorch implementation of Densely Connected Time Delay Neural Network
dover-lap
Python package for combining diarization system outputs.
KeepChatGPT
让我们在使用ChatGPT过程中更高效、更顺畅，完美解决ChatGPT网络错误，不再频繁地刷新网页，足足省去10个多余的步骤。还可以取消后台监管审计。解决了这几类报错: (1) NetworkError when attempting to fetch resource. (2) Something went wrong. If this issue persists please contact us through our help center at help.openai.com. (3) This content may violate our content policy. (4) Conversation not found.
Conv-TasNet
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
dscore
Diarization scoring tools.
pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
CSS_with_Conformer
Code for the ICASSP-2021 paper: Continuous Speech Separation with Conformer.
AK-DE-biGRU
Improving Response Selection in Multi-turn Dialogue Systems by Incorporating Domain Knowledge
webpack
A full-featured Webpack + vue-loader setup with hot reload, linting, testing & css extraction.
kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
VBx
Variational Bayes HMM over x-vectors diarization
d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被60多个国家的400多所大学用于教学。
ml-visuals
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
longformer
Longformer: The Long-Document Transformer
SoftPool
[ICCV 2021] Code for approximated exponential maximum pooling
clash_for_windows_pkg
A Windows/macOS GUI based on Clash
CNN_Component
基于Tensorflow2卷积神经网络即插即用模块实现
Res2Net-PretrainedModels
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
MFR
Masked Face Recognition System