Audio Classification with Machine Learning

Explore audio classification using machine learning in this 43-minute EuroPython Conference talk. Discover how to build practical models that classify sound by converting audio into spectrograms and applying convolutional neural networks. Learn to use Keras and TensorFlow frameworks, and master techniques for achieving usable results with limited data, including transfer learning, audio embeddings, and data augmentation. Gain insights into the applications of sound classification in speech recognition, music analysis, medical diagnostics, manufacturing quality control, and animal behavior studies. A basic understanding of machine learning is recommended, with familiarity in digital sound being beneficial.