11- Preprocessing audio data for Deep Learning

In this video, I show how to get audio data ready for deep learning applications using Python and an audio analysis library called Librosa. Starting from an audio file, I perform the Fourier Transform to extract the power spectrum and the spectrogram. I also show how to extract MFCCs and visualise all features. Code: Preprocessing audio data for deep learning/code Melodrive: Valerio’s Lin