Pinned Repositories
colabtools
Python libraries for Google Colaboratory
course-v3
The 3rd edition of course.fast.ai
courses
Course materials for the Data Science Specialization: https://www.coursera.org/specialization/jhudatascience/1
ctc
Speech recognition with CTC in Keras with Tensorflow backend
ctc_tensorflow_example
CTC + Tensorflow Example for ASR
Cutout
2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552
deep-image-prior
Image restoration with neural networks but without learning.
DeepDenoisingAutoencoder
Tensorflow implementation for Speech Enhancement (DDAE)
SpeechDenoisingWithDeepFeatureLosses
Speech Denoising with Deep Feature Losses
tensorflow
An Open Source Machine Learning Framework for Everyone
jbgh2's Repositories
jbgh2/course-v3
The 3rd edition of course.fast.ai
jbgh2/ctc
Speech recognition with CTC in Keras with Tensorflow backend
jbgh2/Cutout
2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552
jbgh2/deep-image-prior
Image restoration with neural networks but without learning.
jbgh2/SpeechDenoisingWithDeepFeatureLosses
Speech Denoising with Deep Feature Losses
jbgh2/DNP
Audio Denoising with Deep Network Priors
jbgh2/END-TO-END-SPEECH-ENHANCEMENT-BASED-ON-DISCRETE-COSINE-TRANSFORM
jbgh2/fider
Open platform to collect and prioritize product feedback
jbgh2/Hands-On-Generative-Adversarial-Networks-with-Keras
Hands-On Generative Adversarial Networks with Keras, published by Packt
jbgh2/handson-ml2
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
jbgh2/MetricGAN
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (ICML 2019)
jbgh2/n2v
This is the implementation of Noise2Void training.
jbgh2/Noise2Noise-audio_denoising_without_clean_training_data
Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.
jbgh2/noise2self
A framework for blind denoising with self-supervision.
jbgh2/Porcupine
On-device wake word detection powered by deep learning.
jbgh2/python-pesq
PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users using cython
jbgh2/real-time-collaborative-text-editor
A rich-text collaborative editor which allows multiple users to edit the same document at the same time. Uses CRDT and web-socket for real-time collabroation
jbgh2/RedGate.Metrics
Metric generation used at Redgate Software
jbgh2/rnnoise
Recurrent neural network for audio noise reduction
jbgh2/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
jbgh2/SpectralNormalizationKeras
Spectral Normalization for Keras Dense and Convolution Layers
jbgh2/Speech-denoise-Autoencoder
Speech denoiser model using Keras
jbgh2/speech-denoising-wavenet
A neural network for end-to-end speech denoising
jbgh2/tensorflow2-generative-models
Implementations of a number of generative models in Tensorflow 2. GAN, VAE, Seq2Seq, VAEGAN, GAIA, Spectrogram Inversion. Everything is self contained in a jupyter notebook for easy export to colab.
jbgh2/tf_unet
Generic U-Net Tensorflow implementation for image segmentation
jbgh2/TLSphinx
Swift wrapper around Pocketsphinx
jbgh2/VisNetwork.Blazor
Blazor component for vis-js/vis-network javascript library.
jbgh2/warp-ctc
Fast parallel CTC.
jbgh2/Wave-U-Net
Implementation of the Wave-U-Net for audio source separation
jbgh2/Wave-U-Net-For-Speech-Enhancement
Improved speech enhancement with the Wave-U-Net, a deep convolutional neural network architecture for audio source separation, implemented for the task of speech enhancement in the time-domain.