February 2018
Intermediate to advanced
378 pages
10h 14m
English
Audio feature extraction. The IntuneFeatures framework contains code to generate features from audio files and feature labels from the respective MIDI files. It currently supports these features: Log-scale spectrum power estimate by bands, spectrum power flux, peak power, peak power flux, and peak locations.
The CompileFeatures command line app takes audio and MIDI files as input and generates HDF5 databases with the features and the labels. These HDF5 files can then be used to train a neural network for transcription or related tasks.
Read now
Unlock full access