🐦 Audio Classification using CNN

This project focuses on classifying bird sounds from the kaggle Dataset by converting audio signals into mel-spectrograms and applying CNN-based image classification techniques to identify different bird species.

📂 Dataset

For the dataset, refer to the Sound of Bird species on Kaggle.

Approach

1. Convert audio recordings into spectrogram images.
2. Preprocess and normalize the spectrogram data.
3. Train a CNN model to classify different bird species.
4. Evaluate the model on test data.

🚀 Technologies Used

• Python
• TensorFlow Keras
• Librosa (for audio processing)
• Matplotlib & Seaborn (for visualization)