Jibin Wu's Projects
The source code linked to the IEEE JSTSP paper entitled "Parameter tuning-free missing-feature reconstruction for robust sound recognition"
:robot::art::guitar:A curated list of awesome projects, works, people, articles, and resource for creating art (including music) with machine learning. It's machine learning art.
A binary neural network trained for sound localization (0,1)
Binarized Neural Network (BNN) for pytorch
CARLsim is an efficient, easy-to-use, GPU-accelerated software framework for simulating large-scale spiking neural network (SNN) models with a high degree of biological detail.
Carnegie Mellon University 15-213: Introduction to Computer Systems (ICS)
A PyTorch implementation of "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation"
Experiments with Deep Learning
This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.
Environmental-Sound-Classification with binary neural network
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
an imagenet example in torch.
My personal web page repository. https://liuliu-cs.github.io
Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning
Profiling power consumption of a neuromorphic keyword spotter.
The official release of the progressive tandem learning framework.
95.16% on CIFAR10 with PyTorch
Simple examples to introduce PyTorch
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.
Supervised Spiking Network
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
Pytorch-Kaldi implementation of SNN-based ASR systems
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
High-speed simulator of convolutional spiking neural networks with at most one spike per neuron.