All Projects → haoxiangsnr → A Convolutional Recurrent Neural Network For Real Time Speech Enhancement

haoxiangsnr / A Convolutional Recurrent Neural Network For Real Time Speech Enhancement

A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorch

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to A Convolutional Recurrent Neural Network For Real Time Speech Enhancement

Deepseqslam
The Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-60.16%)
Mutual labels:  cnn, rnn
Cnn lstm for text classify
CNN, LSTM, NBOW, fasttext 中文文本分类
Stars: ✭ 90 (-26.83%)
Mutual labels:  cnn, rnn
Nlp overview
Overview of Modern Deep Learning Techniques Applied to Natural Language Processing
Stars: ✭ 1,104 (+797.56%)
Mutual labels:  cnn, rnn
Rnn Theano
使用Theano实现的一些RNN代码,包括最基本的RNN,LSTM,以及部分Attention模型,如论文MLSTM等
Stars: ✭ 31 (-74.8%)
Mutual labels:  cnn, rnn
Codesearchnet
Datasets, tools, and benchmarks for representation learning of code.
Stars: ✭ 1,378 (+1020.33%)
Mutual labels:  cnn, rnn
Neural Networks
All about Neural Networks!
Stars: ✭ 34 (-72.36%)
Mutual labels:  cnn, rnn
Sleepeegnet
SleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach
Stars: ✭ 89 (-27.64%)
Mutual labels:  cnn, rnn
Sincnet
SincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+521.14%)
Mutual labels:  cnn, speech-processing
Captcharecognition
End-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别
Stars: ✭ 97 (-21.14%)
Mutual labels:  cnn, rnn
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-21.14%)
Mutual labels:  cnn, rnn
Deepfakes video classification
Deepfakes Video classification via CNN, LSTM, C3D and triplets
Stars: ✭ 24 (-80.49%)
Mutual labels:  cnn, rnn
Torchsketch
Stars: ✭ 113 (-8.13%)
Mutual labels:  cnn, rnn
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-81.3%)
Mutual labels:  cnn, rnn
Keras Sincnet
Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (-61.79%)
Mutual labels:  cnn, speech-processing
Eda nlp
Data augmentation for NLP, presented at EMNLP 2019
Stars: ✭ 902 (+633.33%)
Mutual labels:  cnn, rnn
Recursive Cnns
Implementation of my paper "Real-time Document Localization in Natural Images by Recursive Application of a CNN."
Stars: ✭ 80 (-34.96%)
Mutual labels:  cnn, real-time
Multi Class Text Classification Cnn Rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
Stars: ✭ 570 (+363.41%)
Mutual labels:  cnn, rnn
Tensorflow cookbook
Code for Tensorflow Machine Learning Cookbook
Stars: ✭ 5,984 (+4765.04%)
Mutual labels:  cnn, rnn
Pytorch Pos Tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Stars: ✭ 96 (-21.95%)
Mutual labels:  cnn, rnn
Mnist Classification
Pytorch、Scikit-learn实现多种分类方法,包括逻辑回归(Logistic Regression)、多层感知机(MLP)、支持向量机(SVM)、K近邻(KNN)、CNN、RNN,极简代码适合新手小白入门,附英文实验报告(ACM模板)
Stars: ✭ 109 (-11.38%)
Mutual labels:  cnn, rnn

A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement

A minimum unofficial implementation of the A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement (CRN) using PyTorch.

ToDo

  • [x] Real-time version
  • [x] Update trainer
  • [x] Visualization of the spectrogram and the metrics (PESQ, STOI, SI-SDR) in the training
  • [ ] More docs

Usage

Training:

python train.py -C config/train/baseline_model.json5

Inference:

python inference.py \
    -C config/inference/basic.json5 \
    -cp ~/Experiments/CRN/baseline_model/checkpoints/latest_model.tar \
    -dist ./enhanced

Check out the README of Wave-U-Net for SE to learn more.

Performance

PESQ, STOI, SI-SDR on DEMAND - Voice Bank test dataset, for reference only:

Experiment PESQ SI-SDR STOI
Noisy 1.979 8.511 0.9258
CRN 2.528 17.71 0.9325
CRN signal approximation 2.606 17.84 0.9382

Dependencies

  • Python==3.*.*
  • torch==1.*
  • librosa==0.7.0
  • tensorboard
  • pesq
  • pystoi
  • matplotlib
  • tqdm

References

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].