Chordify - A Musical Chord Recognizer
The aim of this project is to build a classifier to classify different music samples into a predefined set of chords. We attempt Automatic Chord Extraction, which is the task of assigning chord labels and boundaries to a piece of musical audio, with minimal human involvement.
Chord recognition is the process of detecting a chord from a piece of audio. The transcription of chords has been carried out manually which is tiresome, time-consuming and involves the knowledge of music. Pitch is defined as the perceptual ordering of sounds on a frequency scale, and is approximately proportional to the logarithm of frequency. Pitches can be described as a combination of letters and numbers, where each pitch comes from a set of 12 pitch classes = {C, C#, D, D#, E, F, F#, G, G# A, A#, B#}. A Chord is 3 or more pitches sounded simultaneously or functioning as if sounded simultaneously.
The problem statement can be stated as : Given a music audio, can we determine the sequence of chords present in that it?
Read the final report for further information.