Pitch and Intensity Analysis

This project analyzes the pitch (fundamental frequency) and intensity (loudness) of audio recordings using Parselmouth (Praat) and computes additional audio features via librosa. It provides visualizations and extracts metrics such as MFCCs, spectral centroid, and spectral bandwidth.

Features

• Extract and plot pitch (F0) and intensity contours using Parselmouth
• Compute additional audio features with librosa:
  • Mel-Frequency Cepstral Coefficients (MFCCs)
  • Spectral Centroid
  • Spectral Bandwidth
• Visualize analyses using matplotlib

Installation

1. Clone the repository

git clone https://github.com/<username>/<repository>.git
cd <repository>

2. (Optional) Create a virtual environment

python3 -m venv venv
source venv/bin/activate   # On Windows: venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

If you don’t have a requirements.txt, install manually:

pip install numpy matplotlib parselmouth librosa soundfile jupyter

Usage

1. Place your audio file in the project root or specify its path in the notebook. Example files:

   • /content/Audio for conversation conv_01k0p7nybafrath2av1gy1cxkx.mp3
   • your_audio_file.mp3

2. Launch Jupyter Notebook:

   jupyter notebook

3. Open Pitch_and_intesity_analysis.ipynb and run all cells.

4. If needed, update the audio file path in the first code cell:

   audio_path = "your_audio_file.mp3"

Example Output

• Pitch contour over time
• Intensity (dB) contour over time
• MFCC heatmap
• Spectral centroid and bandwidth graphs

Requirements

• Python 3.8+
• numpy
• matplotlib
• parselmouth
• librosa
• soundfile
• Jupyter Notebook

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the MIT License.

Contact

For questions or feedback, contact Your Name.