MAIA Suggest!
With strong ties to academia, MAIA considers very seriously the fair and
appropriate use of material from others. For the Euro {melody, chords, bass} material we used in this project, we conducted "originality
analyses"
(Yin, Stepney, Reuben & Collins, 2021;
Collins & Laney, 2017)
using the cardinality score
(Janssen, Collins, & Ren, 2019),
as well as other analyses, to establish that generated passages did
not take too much consecutive material from a single, original, input
song.
Background
Artificial intelligence (AI) has been defined as
"The performance of tasks, which, if performed by a human, would be
deemed to require intelligence" (Wiggins, 2006, p.450),
reading between the lines somewhat of Turing's
(
1950)
famous paper. AI methods can be applied to multiple music-analytic and
music-creative activities. Here, we consider AI applied to the activity
of songwriting.
A main topic of
Collins' (2011) PhD
and a couple of subsequent papers
(Collins et al., 2016;
Collins & Laney, 2017)
was concerned with automatically extracting the entire hierarchical
structure from an existing piece of music, and using that structure to
guide a local generative process, so that generated material had
more convincing long-term structure and phrasing, compared to existing
work.
For this interface however, it seemed more appropriate to use the
MAIA Markov
algorithm to generate shorter, four-bar passages for human musicians to experiment
with and combine into longer-term structures.
Ethics/legal
This interface arose out of a
collaboration with Imogen Heap.
Imogen and Tom had a long chat in early February 2020, and one of the
topics we covered was the questionable ethics and legality of deriving
new material from existing, copyright material without permission and/or
proper attribution.
In Tom's opinion, the ethical and legal implications of deriving new
from old material centres on a perceptually valid empirical analysis
(such as the "originality" or "creativity" analyses conducted in
Yin, Stepney, Reuben & Collins, 2021 or
Collins & Laney, 2017, section 3.3).
If it can be shown that a generated passage is no more derivative
of a corpus than other songs from that same corpus, then the reuse of
material is acceptable. If a generated passage does derive more from a
corpus than other songs, then the resue is not acceptable.
For example, one can't copyright an isochronous bass-drum pattern
because such patterns are ubiquitous, whereas one can copyright a
sequence of events (notes, chords, etc.) that is novel with respect to
the corpus of existing music. Existing research on distinctivity is also worth a read here (Collins et al. 2016; Conklin, 2010).
Replicability
The source code for these models is available as an NPM package called
MAIA Markov,
v.0.0.30. The metadata (md), state-transition matrices (stm), and initial
distributions (id) that combine with MAIA Markov to enable replication
of the results above can be downloaded via the following links.
-
Gospel/pop melody.
[stm],
[id].
-
Gospel/pop chords.
[stm],
[id].
-
Gospel/pop bass.
[stm],
[id].
-
Gospel/pop bass.
[stm],
[id].
AI details
The
MAIA Markov algorithm
uses an empirically-derived
Markov model
to generate "new" music in the style of a corpus of existing music. An
article we wrote for Significance magazine provides a good
lay- or young person's introduction to how this works
(Collins, Laney, Willis, & Garthwaite, 2011).
If/when you're ready for heavier stuff, the main references are my PhD
thesis
(Collins, 2011)
and two subsequent papers
(Collins et al., 2016;
Collins & Laney, 2017).
Of these, Collins and Laney (2017)
is probably the best starting point.
I have made some tweaks and improvements to the algorithm since 2017,
and I am currently writing these up for a peer-reviewed journal, but the
main approach is the same. It is worth noting that a Markov model is
not a deep learning algorithm – or even an
artificial neural network, both of which are very popular right now. I
do conduct research on these approaches too, but so far I prefer the
Markov modeling approach because it has stronger cognitive
plausibility in terms of the way I learnt to create
music – analysing states (e.g., notes or chords)
in a certain tonal and temporal context, and formulating and exploring
possibilities for how certain states tend to lead to others.
