Skip to content

Latest commit

 

History

History
80 lines (57 loc) · 2.07 KB

README.md

File metadata and controls

80 lines (57 loc) · 2.07 KB

Audio Emotion Detector

Python NumPy Made with Sklearn

Python 3.7.2


This repo contains Python implemenation for audio emotion detection using Support Vector Machines (Sklearn library)

Dataset used : The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS)

Results


Confusion Matrix

Confusion Matrix

GUI using Tkinter

gui

Usage

Note: Below commands are intended to be run in Git bash

  • Clone the repository
git clone [email protected]:PrashanthaTP/audio-emotion-detector.git
  • Create virtual environment
cd audio-emotion-detector
python -m venv .
  • Activate virtual environment
source Scripts/activate
  • Install dependencies
pip install -r requirements.txt
  • Run gui.py
cd emotion_detector
python gui.py

Dataset Reference

@dataset{livingstone_steven_r_2018_1188976,
  author       = {Livingstone, Steven R. and
                  Russo, Frank A.},
  title        = {{The Ryerson Audio-Visual Database of Emotional
                   Speech and Song (RAVDESS)}},
  month        = apr,
  year         = 2018,
  note         = {{Funding Information Natural Sciences and
                   Engineering Research Council of Canada:
                   2012-341583  Hear the world research chair in
                   music and emotional speech from Phonak}},
  publisher    = {Zenodo},
  version      = {1.0.0},
  doi          = {10.5281/zenodo.1188976},
  url          = {https://doi.org/10.5281/zenodo.1188976}
}