https://github.com/jcsilva/deep-clustering

https://github.com/jcsilva/deep-clustering

Last synced: 8 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/jcsilva/deep-clustering
• Owner: jcsilva
• Created: 2016-09-27T16:48:38.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-02-16T12:46:22.000Z (over 7 years ago)
• Last Synced: 2024-02-28T21:33:01.634Z (4 months ago)
• Language: Python
• Size: 61.5 KB
• Stars: 71
• Watchers: 12
• Forks: 35
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Lists

• awesome-deeplearning-resources - Keras implementation of Deep Clustering

README

        
# Keras implementation of [Deep Clustering paper](https://arxiv.org/abs/1508.04306)

This is a keras implementation of the Deep Clustering algorithm described at https://arxiv.org/abs/1508.04306. It is not yet finished. Most of this code was implemented by [Valter Akira Miasato Filho](https://github.com/akira-miasato). 

Requirements

------------

1. System library: 

  * libsndfile1 (installed via apt-get on Ubuntu 16.04)

2. Python packages (I used Anaconda and Python 3.5):

  * Theano (pip install git+git://github.com/Theano/Theano.git)

  * keras (pip install keras)

  * pysoundfile (pip install pysoundfile)

  * numpy (conda install numpy)

  * scikit-learn (conda install scikit-learn)

  * matplotlib (conda install matplotlib) (only used for visualization)

Training the network

--------------------

First of all, you must create two text files: train\_list and valid\_list. They must contain your training and validation data. The lines of these files must be according to the following pattern:

```

path/to/audioFile1 spk1

path/to/audioFile2 spk2

path/to/audioFile3 spk1

```

spk1, spk2 identifies the speaker that uttered the recorded sentence. 

The current implementation should work with any sample rate, but experiments were conducted only with 8kHz audio. It was already tested with flac and wav files, but it should work with all formats supported by [pysoundfile/libsndfile](http://www.mega-nerd.com/libsndfile/#Features).

After creating train\_list and valid\_list, you may start training the network with the command:

```

python main.py

```

Please check the main script if you wish to use other features from this project, such

as output visualization and prediciton.

As of February, 2017, this project is halted, but we are still open to feedback and questions.

References

----------

* https://arxiv.org/abs/1508.04306