Entry #020



FINAL RELEASE

Hello world,
the video below is the final piece for this project. I will share my experience and additional technical details along with documentation in the following post.
Here I’m sharing the artist statement and the video itself. I hope you will enjoy it.

ARTIST STATEMENT:
This artwork is an exploration of the machine and human interaction, and the properties of the space that, this kind of relationship creates. It examines aspects of this connection, what can be conveyed through art, what is lost through this, and what is unique to this collaboration. This multimedia performance is the result of the continual synthesis between artist, machine and dancer. The result can be understood as co-creation between human and machine – an inimitable, distinctive artwork which is the consequence of mingling of human expression and machine programming, complete with glitches. This investigation through mimetic process invites questions such as whether the machine is a separate entity, or an extension of our humanity; and how what is gathered and formed through the creative process of re-encoding ambiguity and authenticity becomes real, beyond physicality.

Notes:
The work is displayed on the website, dedicated to host the final project along with students from year 1 to 3 from the Digital Arts and Computing module at Goldsmiths University.
The direct link to this work is here.


FLOW OF GLITCHES

For the best experience, please use headphones!



Entry #019



Visual alternatives

                                         
Hello world,

As I promised in a previous post, I’m showing you experimentation with the aesthetic at the finishing phase of the project.
This styling will most probably not make it to the finals, so for that reason, I’m sharing it here and now.
I love the idea of these forms and colours and will likely explore this direction further for another project.
This effect is achieved in MAX MSP through playing with the blending mode during merging two media.

    




Entry #018



ACT #3 Sneek peak.

Hello world,

the video below is the 3rd and the last in this series. The video is edited by now, and with that, I can now proceed to finish the last layers of the artwork. 
This part of the performance is about self-realisation, self-expression and phasing out into a decay. The final pose of the dancer(the starting position in Act#1 – child-pose) suggests, that another cycle is on its way, but in a different form.
The next stage in the process is finishing the artwork by feeding it through my p5.js sketch, before the final post-processing can take place. 


ACT #3 sneak peek.



Entry #017



ACT #2 Sneek peak.

Hello world,

the video below is the second in the series of three. The footage is still a bit raw, and no effect applied, but this is where it is going. I tried some colour accents(which I will post you to see in the next post), however, I’m still in favour of the black and white styling.
This part of the performance is about self-inquiry, self-exploration and reaching some threshold after the awakening from one state to another.
The following ACT(Act3) will narrate the cycle of self-realisation and self-expression.


ACT #2 sneak peek.



Entry #016



ACT #1 Sneek peak.

Hello world,

the video below is the first in the series of three. The footage is still a bit raw, and the effect is not the final one, however, the direction of the style is set for this ACT(the division of the parts of the performance borrowed from the theatre).
This part of the performance is about awakening from one state to another -the coming from the deep within.
The following ACT will look a bit different in comparison to the last one, as it is meant to narrate the next cycle in the process of transformation.


ACT #1 sneak peek.



Entry #015



SOUND AND VISUAL DESIGN

                                             
Hello world,

at this point in the process, Im experimenting with the sound and visuals jointly, as it is time to slowly bring every thread together.
Elettra (the dancer) was so kind as to sketch out some moves based on the previous sound snippets I created.
Im very happy with the movements, visuals and sound. This is not the final of course, however a good direction.
This new sound snippet is created as a creative response to her dance movements. The next step is to do the sound and the movements in real-time with OSC connecting the dancer’s keypoints to some of the sound variables.
Im undecided between black and white feel or on the other hand, I could add some colours to it – maybe both.

 


SOUND AND VISUAL SNIPPET



Entry #014



SOUND DESIGN


Hello world,
I made some sound samples as a means of exploration of the direction of the sound in the artwork.
The title of the piece(Flow) made me think of the actual thing flow reminded me of – in the context of this artwork.
When I mean flow, I do not necessarily think exclusively about the flow of materials, e.g. like water or air, but also the flow of intervals, flow from one state to another, the flow of moments, sounds, fields, thoughts, mindset, outlook… etc.
Flow indicates a place or state one flows to another, and this creates duality. A from – to state. How we could perceive flow other than a linear duality?
If I try to think of – Transmutation as a flow of intervals, but it still appears in duality.

I like this sound bites, as it evokes some deeper feeling in me, something older than my awareness. It feels like it is coming from my deepest, darkest and wildest.
I will follow this thread in my creative research as a possible element in this artwork.




Entry #013



MODULE  – ML POSE ESTIMATION.



Hello world,
This is a brief update on the progress of the project.

This project is about creating a space and a tool for human-machine interaction as a means for creating art.
Since the proposal, I manage to narrow down* the ML elements from the initial four, down to possible two (pose estimation and voice command), already incorporated into the base code.
The final piece going to be exhibited as documentation of an existed performance in the form of a multimedia piece.
The next steps are involving adding more expressive elements like flocking, building in sound synthesis and deciding the choreography (if any) and assigning which elements to control by both the code and the artist.

 

* the other two ML styles could potentially add to the artwork, however the contribution is not proportional to the complications they adding to it. Face detection would make more sense with more than one performing artist, as it could classify and deploy different aesthetics to each dancer. In this case, the object detection does not have any unique function, so it could be delegated to the pose estimation technique.


 


A short video with pose estimation and style transfer.


Entry #012



MODULE  – ML Style Transfer.



Hello world,

This element of the artwork is about experimenting with style transfer. This “Machine Learning” technique does what is saying, transferring a style of one image to another one.
The “style image” and the “content image” ratio in the “result image” depends on the settings we impose on the model before training. It can warry from 1:1 ratio to anything 1.5:1, 1:2 and so on.
To find the right ratio is by no means is an easy task. It is a trial and error process, which could take hours and days to produce.
Finding mutually complimenting “style image” and the “content image” is also a matter of time and patience.
When all goes well, a model will produce something very unique and interesting – and all of a sudden it was worth it.

 


I have tried many style images for transfer, some worked better than others.


Transmutation – process.


Entry #011



MODULE  – ML Speech to Command.



Hello world,

This element of the artwork is testing speech commands. A “Machine Learning” technique for sound classification. It is done by analysing the sound fed through the ML model and making judgements on the voice of the detected subject. Estimating the words received through the microphone into the model, which then compares it for the best match with the words trained beforehand.
I was fiddling with the out of the box model from Google, but I will probably train my own model if I decide to use this technique in my final artwork. Google’s model is good enough for basic things, but biased and trained on other people, so the accuracy is not as great and personalised as it could get.
I was exploring the utility of giving commands via words in the context of this project. I imagine I will possibly assign some visual elements, activate modes of operation, give commands, change variable values or other functionality not foreseen at this point.
Thes visuals not resembling the aesthetic direction of the project, but simply illustrating an exercise.


    


Testing the machine learning model along with the visuals.