Debang Liu's Projects
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Javascript library for precise tracking of facial features via Constrained Local Models
Facial landmark detection based on deep convolutional neural network.
A PyTorch implementation of "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation"
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
deep clustering method for single-channel speech separation
TensorFlow implementation of cascade CNN, trained level-by-level
Speech Recognition using DeepSpeech2.
A toolkit for making real world machine learning and data analysis applications in C++
Computer Vision model to detect face in the first frame of a video and to continue tracking it in the rest of the video. This is implemented in OpenCV 3.3.0 and Python 2.7
💎 Detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Face Tracking library using iCCR
:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures
Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'
A face detection algorithm
Python-based optical flow toolkit for existing popular dataset
Fast, accurate and easy to run dense optical flow with python wrapper
This library provides common speech features for ASR including MFCCs and filterbank energies.
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)
This is the PyTorch implementation of VGG network trained on CIFAR10 dataset
Speech recognition module for Python, supporting several engines and APIs, online and offline.
Stanford dl excercise
Speech separation with utterance-level PIT experiments
Audio-Visual Speech Separation with Cross-Modal Consistency