Skip to content

Can we build a neural network that can tell the difference between Stephen Colbert and Conan O'Brien? Yes, yes we can!

Notifications You must be signed in to change notification settings

IBMDeveloperUK/Audio-Classification-w.-Convolutional-Neural-Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Audio Classification w. Convolutional Neural Networks

In this workshop you will learn how to construct a densely connected convolutional neural network using Keras with a Tensorflow backend to classify spectrograms of audio files of 1 of n speakers (golly, that's dense...).

ahem

In this workshop, you'll learn how to tell which of two people is speaking - namely Stephen Colbert or Conan O'Brien - with neural networks.

The workshop is aimed at people who are interested in learning about machine learning.

Getting Started with Jupyter Notebooks

Jupyter notebooks are an open-source web application that allows you to create and share documents that contain live code, equations, visualizations and explanatory text.

In this workshop we will use IBM Watson Studio to run a notebook. For this you will need an IBM Cloud account. The following steps will show you how sign up and get started. When you have the notebook up and running we will go through the notebook.

IBM Cloud

  • Sign up for an IBM Cloud account

  • When you are signed up click Create Resource at the top of the Resources page. You can find the resources under the hamburger menu at the top left:

An image showing the locations of the 'Create Resource' button

  • Search for Watson Studio and click on the tile:

  • Select the Lite plan and click Create.
  • Go back to the Resources list and click on your Watson Studio service and then click Get Started.

An image if the IBM Cloud Catalog

IBM Watson Studio

1. Create a new Project

  • You should now be in Watson Studio.
  • Create a new project by clicking on Get Started and New Project, or Create Project
  • Give your Project a name.
  • Select an Object Storage from the drop-down menu or create a new one for free. This is used to store the notebooks and data. Do not forget to click refresh when returning to the Project page.
  • click Create.

2. Load and run a notebook

  • Add a new notebook. Click Add to project and choose Notebook:

An image showing the user how to create a notebook

  • Choose new notebook From URL. Give your notebook a name and copy the URL https://github.com/IBMDeveloperUK/Audio-Classification-w.-Convolutional-Neural-Networks/blob/master/conan_or_colbert.ipynb
  • The notebook will load.

You now have the code and resources to run the workshop. Further instructions and information can be found in the notebook.

About

Can we build a neural network that can tell the difference between Stephen Colbert and Conan O'Brien? Yes, yes we can!

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published