l2009312042's repositories
key_word_search
kaldi kws pipline
ActivityNet
This repository is intended to host tools and demos for ActivityNet
CAT
A CRF-based ASR Toolkit
CNN_LSTM_CTC_Tensorflow
CNN+LSTM+CTC based OCR implemented using tensorflow.
Deep-Image-Matting
This is tensorflow implementation for paper "Deep Image Matting"
Hidden-Two-Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Key-word-spotting-DNN-GRU-DSCNN
key word spotting GRU/DNN/DSCNN
k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
Optical-Flow-Guided-Feature
Implementation Code for OFF
pytorch-kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
rnnt-speech-recognition
End-to-end speech recognition using RNN Transducers in Tensorflow 2.0
Speech-Enhancement-Noise-Suppression-Using-DTLN
Speech Enhancement: Tensorflow 2.x implementation of the stacked dual-signal transformation LSTM network (DTLN) for Noise Suppression.
tf-pose-estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Xception1d
Xception1d implementation for audio categorization