Week 1: Data Preprocessing and Exploration
Week 2: Model with Classical ML Algorithms
Week 3: Model with Neural Networks
- Exploration of both multiple data types.
- Performing pre-preprocessing steps on different data types, including cleaning, feature engineering, and feature extraction.
- Download and try some examples of RAVDESS audio speech emotion data.
- Create your example emotional speech for all of the emotion caterogies by recording your voice. Try to use a similar setting/sentence length with the RAVDESS audio examples.
- Add your new audio files to your own OneDrive with a shared link for us to access. Make sure we have "view" permissions. Copy this link for your report.
- Combine your voice data with the rest of RAVDESS, by making sure you follow the file naming conventions.
- Clone the jupyter notebook into your repository on github.
- Perform the same analysis on the combined dataset. [Feature analysis and cleaning, write about the differences between RAVDESS and your dataset]
- Commit the changes in your repository, if any.
Write a 1–page report on the analysis that you have performed with the combined dataset, add images. Add a link to your github and shared dataset on OneDrive. Make sure we can access/view them. You can include issues you encountered, how did you solve problems. Upload your report on canvas in PDF format. [between 500-1000 word limit] Cite all your resources, including the datasets as references (outside of page/word limit . Credits: https://github.com/IliaZenkov/sklearn-audio-classification