Uses audio analysis along with a Convolutional Neural Network model to detect emotions in speech.
This project focuses on using audio analysis techniques in combination with a Convolutional Neural Network (CNN) model to detect emotions in speech. It's designed to provide a framework for understanding and recognizing emotions in spoken language, which has practical applications in various fields, including human-computer interaction, sentiment analysis, and mental health monitoring.
- Audio Preprocessing: Utilize audio processing libraries to extract relevant features from speech signals.
- Convolutional Neural Network: Implement a CNN model to learn emotional patterns from audio data.
- Emotion Classification: Identify emotions such as happiness, sadness, anger, and more.
- Visualization: Visualize emotions through graphs, spectrograms, or other graphical representations.
-
Clone the repository to your local machine:
git clone https://github.com/sudocanttype/Auditory_Unveil.git cd Auditory_Unveil -
Install the Python dependencies
pip install -r requirements.txt
-
Run the Jupyter Notebook
jupyter notebook ACM2023.ipynb