naplab / Danet
Licence: mit
Deep Attractor Network (DANet) for single-channel speech separation
Stars: ✭ 54
Labels
Projects that are alternatives of or similar to Danet
Data Privacy For Data Scientists
A workshop on data privacy methods for data scientists.
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Info490 Sp17
Advanced Data Science, University of Illinois Spring 2017
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Challengehub Baselines
ChallengeHub开源的各大比赛baseline集合
Stars: ✭ 54 (+0%)
Mutual labels: jupyter-notebook
Homeless Arrests Analysis
A Los Angeles Times analysis of arrests of the homeless by the LAPD
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Info490 Fa16
INFO 490: Foundations of Data Science, offered in the Fall 2016 Semester at the University of Illinois
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Visualizing And Understanding Convolutional Neural Networks
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Tianchi ship 2019
天池智慧海洋 2019 https://tianchi.aliyun.com/competition/entrance/231768/introduction?spm=5176.12281949.1003.1.493e5cfde2Jbke
Stars: ✭ 54 (+0%)
Mutual labels: jupyter-notebook
Mypresentations
this is my presentaion area .个人演讲稿展示区，主要展示一些平时的个人演讲稿或者心得之类的，
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Pyspark Setup Guide
A guide for setting up Spark + PySpark under Ubuntu linux
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Handwritten Character Recognition
This a Deep learning AI system which recognize handwritten characters, Here I use chars74k data-set for training the model
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Commitgen
Code and data for the paper "A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes"
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Keras2kubernetes
Open source project to deploy Keras Deep Learning models packaged as Docker containers on Kubernetes.
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Tutoriais De Am
Algoritmos de aprendizado de máquina criados manualmente para maior compreensão das suas funcionalidades
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Bts Pytorch
PyTorch implementation of BTS Depth Estimator
Stars: ✭ 54 (+0%)
Mutual labels: jupyter-notebook
Facenet Face Recognition
This is the research product of the thesis manifold Learning of Latent Space Vectors in GAN for Image Synthesis. This has an application to the research, name a facial recognition system. The application was developed by consulting the FaceNet model.
Stars: ✭ 54 (+0%)
Mutual labels: jupyter-notebook
Mastering Python Data Analysis
Mastering-Python-Data-Analysis
Stars: ✭ 53 (-1.85%)
Mutual labels: jupyter-notebook
Deep Attractor Network (DANet) for single-channel speech separation
This repository provides the implementation of the Deep Attractor Network (DANet) for single-channel speech separation in Jupyter Notebook (.ipynb) format. DANet was introduced in the following papers:
Zhuo Chen, Yi Luo, and Nima Mesgarani, Deep attractor network for single-microphone speaker separation
Yi Luo, Zhuo Chen, and Nima Mesgarani, Speaker-independent speech separation with deep attractor network
Informations about the papers can also be found in our lab website.
Citation
If you find the scripts helpful in your research, please consider citing:
@inproceedings{chen2017deep,
title={Deep attractor network for single-microphone speaker separation},
author={Chen, Zhuo and Luo, Yi and Mesgarani, Nima},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on},
pages={246--250},
year={2017},
organization={IEEE}
}
@article{luo2018speaker,
title={Speaker-independent speech separation with deep attractor network},
author={Luo, Yi and Chen, Zhuo and Mesgarani, Nima},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume={26},
number={4},
pages={787--796},
year={2018},
publisher={IEEE}
}
Requirements
- Python 3.6.4
- Pytorch 0.4.1
- h5py 2.7.1
- sklearn 0.19.1
- numpy 1.15.0
- librosa 0.6.0
- jupyter 1.0.0 or above
- notebook 5.4.0 or above
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].