Navigating the Intricacies of Markov Models in Sound
In our latest exploration within the “Mycelium and Sound Collectives” project, we dive deeper into the realm of machine learning, focusing on the pivotal step of feature engineering – transforming raw musical data into a machine-readable format. This process is crucial for our goals, ensuring the data highlights the musical characteristics essential for algorithmic learning and interpretation.
Today, we spotlight our third vlog, which delves into the intricacies of the Markov model through MAX/MSP, showcasing how the ml.markov object’s ‘order’ command significantly expands the model’s memory. This allows it to recognize and generate more complex musical patterns, revealing the potential of machine learning in music composition and improvisation.
This exploration not only enhances our understanding of Markov models but also highlights the importance of precise data preparation in machine learning. By improving how data is fed into the model, we can greatly enhance its predictive capabilities, offering new possibilities for musical creativity at the intersection of technology and art.
Stay tuned as we continue to push the boundaries of music, mycology, and machine learning, uncovering new insights and possibilities in this innovative project.
Following up from my last post, I am going more into detail in the project “Mycelium and Sound Collectives”, working more in depth with the question of musical genre and how to make the musical data ready for the machine learning, a process known as feature engineering.
In this 2nd episode of our vlog, we guide musicians and composers in harnessing the power of the Markov model for music improvisation. We dive into the essentials of machine learning, emphasizing tailored feature engineering for unique musical styles. Through a radar chart analysis, we prioritize key parameters….
Join me in this exploration by watching the vlog episode. If you find it insightful, don’t forget to like and subscribe – you know the drill – but sincerely: your support means a lot. Thanks for tuning in, and stay tuned for more vlog episodes to come!
As a part of my project “Mycelium and Sound Collectives”, I am currently doing some research into the question of machine learning and music.
The project is scheduled for autumn 2024, as an outdoor performance, which introduces a rather peculiar ensemble – an amalgamation of a saxophone player, an analog synth with a computer, and then a rather unconventional performer: a mycelium network forming a fairy ring in the soil where the concert unfolds.
In my current research, I am delving into the intersection of machine learning and music composition, questioning the potential for computers to genuinely improvise music.
My examination uncovers the complexities of the artistic process, exploring choices within sound composition. I scrutinize loop pedals, sequencers, and the Markov model, viewing them not merely as tools but as integral components shaping a dialogue between live musicians and evolving machine capabilities.
As documentation for the process, I am doing a vlog, and in the first episode, I am asking: “Can my computer learn to improvise music?”.
In this vlog episode, I don’t provide a definitive answer to the question posed in the title. Instead, I aim to unfold the various aspects at play when delving into the complexities of this inquiry. This involves discussing diverse examples of machine learning models, ranging from the rudimentary to the advanced, in connection with music. As you’ll see when you are watching it, I also demonstrate their functionality within the MAXMSP software, using concrete sound examples. Additionally, I delve into the conceptual framework essential for making informed artistic choices at the intersection of art and technical solutions.
Join me in this exploration by watching the vlog episode. If you find it insightful, don’t forget to like and subscribe – you know the drill – but sincerely: your support means a lot. Thanks for tuning in, and stay tuned for more vlog episodes to come!
What does the typical contemporary music ensemble look like? I haven’t been able to find an answer to this question, so I decided to make my own enquiry.
There seems to be three categories: Larger ensembles, typically in the format of sinfoniettas. Ensembles in traditional formats, ie. string quartets, wind quintets, etc. And then: ecclectic, new, experimental formats. I have noticed, that when there are call for scores, it seems as if the formats available are most often within the 3rd category.
I decided to make a small investigation into the question, narrowing my research, so I looked for ensembles within the 3rd category, with these conditions:
the ensemble must be active now, 2022
they must be playing composed music (not excluding ensembles also doing other formats)
consisting of from 3 to 10 players
playing acoustic instruments, although ensembles also including electronics were also ok
I gathered info in a google sheet, and here is the result:
I found (sofar) 18 ensembles
They are based in Argentina Australia Denmark Finland France Germany Irland Italy Serbia UK USA
They have between 8 and 3 members
What instruments are they playing?
All in all, these instruments were used: Voice Recorder Flute Obo Saxophone Clarinet Bassoon Trumpet Trombone Guitar Harp Accordeon Piano Percussion Violin Viola Cello Double Bass Electronics
What is the most frequently used instruments?
1
Piano
79%
2
Clarinet
74%
3
Flute
68%
4
Cello
68%
5
Violin
58%
6
Percussion
53%
7
Voice
26%
8
Viola
26%
9
Obo
21%
10
Double Bass
21%
11
Electronics
16%
12
Bassoon
11%
13
Guitar
11%
14
Accordeon
11%
15
Recorder
5%
16
Saxophone
5%
17
Trumpet
5%
18
Trombone
5%
19
Harp
5%
The piano was part of 79% of the ensembles.
Since the average size of these ensembles were 6 players, I found it useful to look at the six most frequently used instruments, marked in bold above, and these are: Piano, Clarinet, Flute, Cello, Violin, Percussion.
What my mini-research has shown, so far, is that the typical ensemble playing contemporary music is a sextet with the so-called Pierrot ensemble with an added percussion player.
Three of these ensembles are consisting of exactly the six most typical instruments, marked in bold. Two ensembles included the six instruments, while adding 1 or 2 others.
Information
I based my search mostly in this “List of contemporary classical ensembles” (wikipedia). It is of course rather incomplete, and many of the listed ensembles are historical. What I find curious is that I had such a hard time finding information on these things online. It is really difficult for me to find updated databases on the current ensembles, and for that matter, festivals, calls for scores, and so on. In short: Information about the contemporary music scene seems to be really scarce.
This leads of course to my typical last words: Help! If you have information about good, updated ressources for contemporary music, composers, festivals, musicians and so on. If you know about more ensembles to include in my enquiry. And, of course, if you know about real, maybe even academic, enquiries into these questions: Help!
Inspired by a comment by Sergio Valdez, I would like to share some thoughts about being an independent researcher.
It’s a huge challenge to be an independent researcher. One thing is the obvious lack of time (a problem, I deal with here), since we need to work in something else to earn a living. Another thing is the lack of access – to networks, to libraries, to journals, to recognition. However, being an independent researcher also means independence from a highly politicized, competitive environment.
In mainstream higher education institutions you have to deal with all sorts of more or less bizarre things, that are putting restrictions to your possibilities to do what you’re supposed to. What I hear from my ‘dependent’ conspecifics is that they are subject to managerial pressure towards a more commercial bottom line kind of approach. At the same time, they are experiencing financial cuts, which puts pressure on their work environment, having to spend more and more time with administrative tasks, and dealing with an increasing number of students.
The trend is towards a more top down approach, where research institutions have to live up to more and more detailed policy demands in order to get the financial support from policy makers. As an example, within the field of Pedagogy, there is the so-called ‘early childhood preventive intervention’ (in Danish: tidlig indsats). This kind of policy induced trend in research has a double edge. On the one hand there is no doubt, that a lot of children need the kind of help, the program is aiming at. On the other, it’s evident that the State has an interest in reducing welfare costs. However, it is crucial to ask what basic understanding of people and their possibilities to be agents in their own lives lies behind this trend. In other words: how can we avoid a patronizing bureaucratization of people’s lives?
Being an independent researcher is an opportunity to realize projects that are disruptive to mainstream research policy agendas. It means an opportunity to be truly critical towards mainstream trends.
What kind of thinking is possible in mainstream higher educational institutions? For one, as I have argued above, policy demands are putting rather clear limits to the content of research. Another thing is what kind of people are included. The environment of Higher Education is excluding a great number of people. For some, the demands to reading-writing skills is an obstacle, whether this is based on social or cognitive reasons. For others, the high level of stress and competition is an obstacle. And there are also those, who have a hard time coping with the intellectual/social/gendered environment of HE, for the reasons I have mentioned above. And then there are those who do not have the economical means to embark on a (precarious) academic career. In short, independent research is a place where we ‘misfits’ are thriving. In this sense, I am beginning to think of this environment as a place for empowerment and resistance, and I suggest we start talking about it in terms of ‘folk research’, ‘deviant research’, and why not give it a nickname: indiesearch?
Building Sound Collectives 