Bird Species Classification from Audio
End-to-end audio classification pipeline using Mel-Spectrograms and deep learning. 70% accuracy on bird species identification.
Implemented an end-to-end pipeline for bird species identification from audio recordings using Mel-Spectrogram representations and deep learning.
Key contributions:
- Audio-to-spectrogram preprocessing pipeline
- CNN-based classifier trained on Mel-Spectrogram features
- 70% accuracy on bird species identification from raw audio