This project aims to develop a speech emotion recognition system using machine learning techniques. The goal is to accurately classify the emotional state of a speaker based on the audio input. Emotion recognition from speech has various applications including but not limited to customer service analysis, mental health monitoring, and human-computer interaction.
Project Structure
data: This directory contains the dataset used for training and testing the emotion recognition model.
models: This directory stores the trained models.
results: Contains evaluation results and any other relevant output generated during the project.
docs: Documentation directory.
requirements.txt: List of dependencies required to run the project.
README.md: Overview and instructions for running the project.
Content:-
There are a set of 200 target words were spoken in the carrier phrase "Say the word _' by two actresses (aged 26 and 64 years) and recordings were made of the set portraying each of seven emotions (anger, disgust, fear, happiness, pleasant surprise, sadness, and neutral). There are 2800 data points (audio files) in total.The dataset is organised such that each of the two female actor and their emotions are contain within its own folder. And within that, all 200 target words audio file can be found. The format of the audio file is a WAV format
Getting Started
Acknowledgments:-
This project was inspired by the growing interest in emotion recognition and its potential applications.
Special thanks to the developers of the libraries and frameworks used in this project.
I wanted to thank University of Toronto for putting together this awesome dataset!
Dataset:-
The dataset used forthis project is storedin the data directory. It consists of audio recordings labeled with corresponding emotion categories. Before using the dataset, ensure proper citation and compliance with licensing terms.
Contributing
Contributions are welcome! If you have any ideas, suggestions, or improvements, feel free to open an issue or submit a pull request.