HOME
        TheInfoList






Pop music automation is a field of study among musicians and computer scientists with a goal of producing successful pop music algorithmically. It is often based on the premise that pop music is especially formulaic, unchanging, and easy to compose. The idea of automating pop music composition is related to many ideas in algorithmic music, Artificial Intelligence (AI) and computational creativity.

Overview: automation in music

Algorithms (or, at the very least, formal sets of rules) have been used to compose music for centuries; the procedures used to plot voice-leading in counterpoint, for example, can often be reduced to algorithmic determinacy. Now the term is usually reserved, however, for the use of formal procedures to make music without human intervention.

Classical music automation software exists that generates music in the style of Mozart and Bach and jazz. Most notably, David Cope[1] has written a software system called "Experiments in Musical Intelligence" (or "EMI") that is capable of analyzing and generalizing from existing music by a human composer to generate novel musical compositions in the same style. EMI's output is convincing enough to persuade human listeners that its music is human-generated to a high level of competence.

Creativity research in jazz has focused on the process of improvisation and the cognitive demands that this places on a musical agent: reasoning about time, remembering and conceptualizing what has already been played, and planning ahead for what might be played next.

Inevitably associated with Pop music automation is Pop music analysis.

Projects in Pop music automation may include, but are not limited to, ideas in melody creation and song development, vocal generation or improvement, automatic accompaniment and lyric composition.

Automatic accompaniment

Some systems exist that automatically choose chords to accompany a vocal melody in real-time. A user with no musical experience can create a song with instrumental accompaniment just by singing into a microphone. An example is a Microsoft Research project called Songsmith,[2] which trains a Hidden Markov model using a music database and uses that model to select chords for new melodies.

Melody generation

Automatic melody generation is often done with a Markov chain, the states of the system become note or pitch values, and a probability vector for each note is constructed, completing a transition probability matrix (see below). An algorithm is constructed to produce and output note values based on the transition matrix weightings, which could be MIDI note values, frequency (Hz), or an

Algorithms (or, at the very least, formal sets of rules) have been used to compose music for centuries; the procedures used to plot voice-leading in counterpoint, for example, can often be reduced to algorithmic determinacy. Now the term is usually reserved, however, for the use of formal procedures to make music without human intervention.

Classical music automation software exists that generates music in the style of Mozart and Bach and jazz. Most notably, David Cope[1] has written a software system called "Experiments in Musical Intelligence" (or "EMI") that is capable of analyzing and generalizing from existing music by a human composer to generate novel musical compositions in the same style. EMI's output is convincing enough to persuade human listeners that its music is human-generated to a high level of competence.

Creativity research in jazz has focused on the process of improvisation and the cognitive demands that this places on a musical agent: reasoning about time, remembering and conceptualizing what has already been played, and planning ahead for what might be played next.

Inevitably associated with Pop music automation is Pop music analysis.

Projects in Pop music automation may include, but are not limited to, ideas in melody creation and song development, vocal generation or improvement, automatic accompaniment and lyric composition.

Automatic accompaniment

Some systems exist that automatically choose chords to accompany a vocal melody in real-time. A user with no musical experience can create a song with instrumental accompaniment just by singing into a microphone. An example is a Microsoft Research project called Songsmith,Mozart and Bach and jazz. Most notably, David Cope[1] has written a software system called "Experiments in Musical Intelligence" (or "EMI") that is capable of analyzing and generalizing from existing music by a human composer to generate novel musical compositions in the same style. EMI's output is convincing enough to persuade human listeners that its music is human-generated to a high level of competence.

Creativity research in jazz has focused on the process of improvisation and the cognitive demands that this places on a musical agent: reasoning about time, remembering and conceptualizing what has already been played, and planning ahead for what might be played next.

Inevitably associated with Pop music automation is Pop music analysis.

Projects in Pop music automation may include, but are not limited to, ideas in melody creation and song development, vocal generation or improvement, automatic accompaniment and lyric composition.

Some systems exist that automatically choose chords to accompany a vocal melody in real-time. A user with no musical experience can create a song with instrumental accompaniment just by singing into a microphone. An example is a Microsoft Research project called Songsmith,[2] which trains a Hidden Markov model using a music database and uses that model to select chords for new melodies.

Melody generation

Automatic melod

Automatic melody generation is often done with a Markov chain, the states of the system become note or pitch values, and a probability vector for each note is constructed, completing a transition probability matrix (see below). An algorithm is constructed to produce and output note values based on the transition matrix weightings, which could be MIDI note values, frequency (Hz), or any other desirable metric.

A second-order Markov chain can be introduced by considering the current state and also the previous state, as indicated in the second table. Higher, nth-order chains tend to "group" particular notes together, while 'breaking off' into other patterns and sequences occasionally. These higher-order chains tend to generate results with a sense of phrasal structure, rather than the 'aimless wandering' produced by a first-order system.[3]

Lyric composition

Automated lyric creating software may take forms such as:

The Tra-la-Lyrics system[4] produces song lyrics, in Portuguese, for a given melody. This not only involves matching each word syllable with a note in the melody, but also matching the word's stress with the strong beats of the melody.

This involves natural language processing. Pablo Gervás[5] has developed a

Automated lyric creating software may take forms such as:

The Tra-la-Lyrics system[4] produces song lyrics, in Portuguese, for a given melody. This not only involves matching each word syllable with a note in the melody, but also matching the word's st

The Tra-la-Lyrics system[4] produces song lyrics, in Portuguese, for a given melody. This not only involves matching each word syllable with a note in the melody, but also matching the word's stress with the strong beats of the melody.

1st-order matrix
Note A C# Eb
A 0.1 0.6 0.3
C# 0.25 0.05 0.7
Eb 0.7 0.3 0