A compact pipeline for detecting emergency vehicles from audio using deep learning. Includes data download and preprocessing, MFCC/LFCC/Chroma feature extraction, model training (autoencoders for dimensionality reduction and FFNN/CNN/LSTM classifiers) and performance evaluation.
deep-learning feature-extraction neural-networks convolutional-autoencoder representation-learning digital-signal-processing unsupervised-learning urban-sound-classification audio-classification autoencoders emergency-response intelligent-transportation-systems smart-city acoustic-event-detection sound-recognition siren-detection feature-compressio
-
Updated
Nov 23, 2025 - Jupyter Notebook