Series:
Part 1 | Part 2 | Part 3 | Part 4 | Part 5 (Final part of this article)
As we have seen, NotePerformer provides an excellent system for reading a score and reconstructing it into stable musical output. Melisma, on the other hand, takes a step further, attempting to enter the domain of how music itself comes into being.
However, what emerges in this process is the limitation of generation as an act.
The modeling of temporal flow and change in monophonic music has already reached a high level.
Yet, in music such as polyphony—where multiple voices interact simultaneously—it becomes clear that learning mere data or patterns is not sufficient.
However, in music such as polyphony, where multiple voices are involved simultaneously, it becomes clear that mere learning of data and patterns is not sufficient.
At that point, something is ultimately required to judge whether the result truly functions as music.
And for now, that role still belongs to human perception—our ears.
And at this point, it is still left to the human hearing, or "ear.
Generative AI can create music based on past data,
but its ability to determine whether that music sounds truly natural or convincing remains limited.
We are not yet fully capable of judging whether the music is truly natural or compelling.
In other words,
You may be able to "make it," but it may still be difficult to "judge it to be good."
Returning to Sequencing
Seen in this light, the fact that I continue to work with manual sequencing may not be accidental, but rather a natural outcome.
Sequencing is not simply about placing notes. It inherently involves a continuous interplay between generation and judgment:
- selecting sounds
- balancing voices
- shaping temporal nuance
- correcting subtle inconsistencies
In this sense, sequencing is not just a method of creating music, but the very process through which music comes into being.
One might even say that humans, often unconsciously, rely on a faculty of evaluation that AI has not yet achieved.
Final Thoughts
Through this series of reflections, what becomes clear is that music is not merely data or structure.
It is something in which relationships evolve over time, and its realization inevitably involves an element of judgment.
Generative AI certainly points toward new possibilities.
At the same time, it also brings into sharper focus the role of the human in music.
And at least for now,
the place where music truly becomes music
remains within the process of listening, thinking, and refining—
a process carried out by human hands and ears.
Japanese version is abailable here.