Skip to content

Latest commit

 

History

History
28 lines (20 loc) · 1.28 KB

README.md

File metadata and controls

28 lines (20 loc) · 1.28 KB

deep-emotion-sense

Convolutional neural network to predict language-independent emotion on a dataset of English and French speech.

This model is trained on a merged dataset of natural speech with data provided by IEMOCAP for english speech samples and Recola for french speech samples.

The implementation is a basis for a research paper on comparison on different optimization algorithms and activation functions.

Getting Started

You can view the notebook here.

Run the notebook

Prerequisites

  • Python 3
  • Tensorflow

Starting the notebook

Simply open a new terminal in the directory and type:

> jupyter notebook

Built With

Contributors