Composing Tips from AI

 

Generative artificial intelligence (GAI) has some tips for composing a piano piece:

• Start with a melody: Begin with a simple melodic phrase and improvise on it. The melody is the focal point of the piece and will lead to the chorus. 
• Consider the form: Think about the style of the piece, whether it's rhythmic or melodic, contemporary or traditional. 
• Use schemata: Standardized two-voice structures like the Circle of 5ths can create a satisfying structure. 
• Add variations and embellishments: Take the melody and extend it by inverting, augmenting, or reversing it. 
• Build excitement: Slowly add excitement and power over the course of the piece. 
• Edit and improve: Know when to stop. 
• Keep it simple: Keep the piece as simple as possible. 

Other things to consider when composing a piano piece include: Choosing a key, Finding a chord progression, Writing lyrics, and Resolving the song. 

Composing music can be a lengthy process, taking anywhere from a few hours to several months. If you're feeling uninspired, try taking a walk, exercising, reading a book, or listening to other music.

 

Human comment: Notice that the hard work is human intelligence and creativity!

AI in Music Composing

 With the advancements in generative artificial intelligence (AU) have emerged questions about its impact on music composing.

Generative artificial intelligence is based on searching through vast data sets of information, in this case, music, to identify patterns. Algorithms provide directions on how to search, categorize, sort and synthesize the resultant data to fit human-developed specifications.

The simplest area of music composition utilizing generative AI tools is lyrics because of the quantity of textual material that is readily available. Other AI tools sift through existing songs to predict variables that are characteristic of popular, profitable compositions. For instance, fast tempos and major keys are more popular. Based on that information, people can give prompts to AI music-generating tools to create melodies and harmonies that audience will enjoy listening too. AIVA (Artificial Intelligence Virtual Arts) can generate pieces that are hard to distinguish from music created by classical composers.

Often the source materials has been gathered without regard to copyright, and lyricists and music publishers are starting to sue companies that develop and promote their AI text generating tools. The plaintiffs are demanding licensing deals and royalties for their works. While copyright allows for compositions that may be based on another work, the new composition must differ significantly not to be confused with the prior work and add new value to the music.  What the composers assert that they are due is consent (permission), credit (attribution), and compensation (typically money).

Nevertheless, AI is not truly creative. It has no feelings and no sense of nuanced context. Were composers to depend on AI tools to write music, the results would probably become more homogenous and duller, certainly not inspiring the listener – or the musician.

Artificial Intelligence and Future Classical Music

 

Tomoko hears and feels the humanity expressed in the piano compositions she plays. But now artificial intelligence can play and compose music, even symphonies. What, if anything, is lost in the process? Could there be a future classic?

As one example, overseen by the Director of the Karajan institute in Salzburg, an international team fed a speech recognition program Beethoven’s nine symphonies and preliminary work on Beethoven’s 10^th  as well as other pieces by his contemporaneous composers. Excerpts can be heard at https://www.youtube.com/watch?v=EAgnSr5t1VI.

As the video demonstrates, Google was able to use algorithms to enable Google users to input a few notes that could be manipulated by an algorithm to “compose” a piece in Bach’s style. Chi Cao’s senior theses consisted of a software program he developed called “AI Classical Music Composer.” This program drew upon music theory and knowledge, which Chi Cao transformed into hundreds of lines of code. In this way, more people could have the opportunity to experience the joy of composing music.

On a commercial basis, Aiva Technologies created the software program called Aiva: Artificial Intelligence Virtual Artist. The inventors used deep learning techniques to “teach” the computer to compose music. The generated pieces have been used for film, ads and gaming soundtracks. The company released a album “Genesis,” and Aiva has been given the official legal status of Composer, including copyright status. As such, Aiva is the first AI to gain this recognition.

The question remains: where is the heart of AI-generated music? Maybe it rests in the ears of the beholder. The Turing test states that if one cannot tell if a person or a computer is responding, then it may be considered artificial intelligence. That process can easily be applied to discerning the difference between human-generated and AI-generated music. Of course, such a test probably says more about the listener than the composition. Tomoko would know the difference….