This tutorial will guide you through some tools for Melody Analysis using the Essentia library (http://www.essentia.upf.edu). Melody analysis tools will extract a pitch curve from a monophonic or polyphonic audio recording. It outputs a time series (sequence of values) with the instantaneous pitch value (in Hertz) of the perceived melody. We provide two different operation modes: 1) using executable binaries; 2) Using Python wrappers.
You can download the executable binaries for Linux (Ubuntu 14) and OSX in this link: http://tinyurl.com/melody-mbricks To execute the binaries you need to specify the input audio file and an output YAML file, where the melody values will be stored.
Locate an audio file to be processed in WAV format (input_audiofile).
Usage: ./streaming_pitchyinfft input_audiofile output_yamlfile
Usage: ./streaming_predominantmelody input_audiofile output_yamlfile
You should first install the Essentia library with Python bindings. Installation instructions are detailed here: http://essentia.upf.edu/documentation/installing.html .
In [1]:
print 'Hello this is Melody analysis'