Category: CONTEMPORARY ISSUES IN SOUND ARTS

(ESSAY RESEARCH)

The concept of a sonic ‘failure’ stems from the mainstream rejection of radical (of the time) sonic concepts, often occurring when creative innovations clash with commercial demands for consistency, engagement, and traditional structures. With money being at the forefront of the corporate music and arts industry, progressive concepts often get rapidly declined due to the uncertainty of their profit. There is a specific mould in which people know will make money, therefore steering away from this formation poses risk, and the mainstream isn’t risky, it is predictable, expected and formulaic. (Most of them time.)

Often times, when rejected by the mainstream world, such concepts are adopted by subcultures, forming a strong community around the discovery, and enhancing the emotional depth of the work. Subcultures are key in art and music, they supply a non-restrictive space for deeper development, allowing concepts to continue to grow in a very ambitious way. They allow for people to put passion over profit. Unlike the corporate view, seeing the work as a commodity, stripping the emotional context away from the art and the artist, leaving only a ‘product’ left.

This tendency of corporate rejection and underground adoption is continuous throughout history, and often times follows a very similar pattern, repeatedly ending in the reabsorption into mainstream media. This reabsorption occurs due to the popularity that surrounds the once ‘radical’ concept. The community formed, create new, innovative works which begin to attract a wider audience due to their experimental, unheard, and imaginative features. This popularity attracts establishments who recognise they can benefit finically from this public engagement. Frequently using rather unethical methods in order to brand the art.

There are many different examples of this pattern occurring, both prior to and in the contemporary world , sonic examples include:

Luigi Russolo’s ‘Intonarumori‘.

(“noise-intoners”)

Russolo was a key figure in the Italian Futurist movement, a patron for noise, he believed the industrial revolution changed the human ear. For Russolo, the traditional orchestra was a limiting sound, he argued that a modern soul required modern sounds and therefore the rigid definitions of music needed expanding and widening.

In 1913, challenging this definition, Russolo introduced ‘intonarumori’, a hand cranked, acoustic noise maker designed to hiss, howl, and rumble, replicating the industrial sounds of the time. Made up of large wooden boxes with a metal speaker horn on the front. Inside, a complex mechanical system of wheels, strings, and membranes producing sound when a hand crank was turned or a lever moved. There were 27 different sounding machines all together, forming their own complex orchestra. Made to represent the soundscape of modernity.

When exhibited to the public at his 1914 Milan debut of ‘intonarumori’, Russolo was confronted with physical hostility from the audience. To listeners raised on the elegance of opera, used to the sounds of Verdi or Puccini, it felt like an auditory assault, a personal insult on the culture of orchestra itself. It was entirely new perspective on performance, something people were not used to and certainly not comfortable in accepting.

This concept of noise was radical for the time and it is artist like Russolo who completely changed the evolution of sound. He impacted the modern views

Facing this reaction from a mainstream audience, Russolo realised the incapacity of fully conveying the revolutionary, transformative essence of his “art of noises” theory. However he didn’t stop and his work was accepted and welcomed with great admiration from people and artists who were able to understand the importance and relevance of this change in tradition.

‘Intonarumori’ wad destroyed in WWII, however replicas have since been produced, for example:

Roland TR- 808 Drum Machine.

A more modern example of this ‘sonic rejection’ is the Roland TR- 808 drum machine. Launched in 1980, introduced as ‘realistic-sounding drums’

Prior to the release of the 808, earlier in the year the Linn LM-1 was released, a drum machine which used high-fidelity digital samples of real drums. Corporate studio musicians became accustomed to using a ‘realistic’ sounding machine.

This is where the commercial downfall of the 808 lay. The memory chips needed to play back sampled recordings of real drum sounds were too expensive, and so the engineers of the 808 used analog synthesis to recreate the sounds. Although a simple choice born of necessity, choosing analog over digital technology was the aspect that made the profound impact on music that 808 eventually had.

Due to Rolands choice to use analogue synthesis, every sound was therefore generated by an electrical circuit, making the audio sound thin and synthetic to artists who were used to the realistic sound of a drum kit. The 808 struggled to find its place in the mainstream music establishment, causing issues that producers and musicians didn’t want to deal with, eventually just disregarding it as a ‘worthy’ machine.

The 808 was discontinued in 1983 after only 12,000 units were made.

Due to the commercial failure of the machine, second hand shops and pawn shops became flooded with them, selling them for a fraction of the original price. They then became available to an entirely new audience, who previously, weren’t able to afford the product.

Early hip hop is what made the 808’s name.

Afrika Bambaataa and the Soulsonic Force used the 808 beat in ‘Planet Rock’, this track is is widely considered the first major hip-hop/electro hit to use it, popularising it as a staple of the genre. 

The 808 was adopted by subcultures of artists who liked the distinct sound of the machine, seeing it as an instrument that wasn’t trying to replicate the realistic sounds of a drum kit, but instead they appreciated the synthetic, robotic and futuristic noises it produced. Musical subcultures in areas of the US such as; the Bronx, Detroit & Miami discovered that the 808’s kick drum was a pure sine wave, meaning, unlike a real kick drum, you could sustain the decay, turning a drum hit into a bass note.

‘Underground’ artists used the 808 in ways it was originally not intended for, however created incredibly inspiring, influential work that changed the sound of genres. So although seen by Roland and the mainstream music industry as a complete failure, people do what they do best and used their creativity to take an existing concept and produce an entirely new perspective of it.

The community that formed around the 808 continued to grow due to the popularity of the genres it became used in. This resulted in the reintegration of the 808 into corporate music. 40 years later, every DAW is pre-loaded with an 808 sound bank.

RAVE is an audio processing, generative tool, designed by Antoine Caillon and the ACIDS research group at IRCAM. RAVE (Realtime Audio Variational autoEncoder) is a learning framework for generating a neural network model from audio data.

As an encoder, it is able to take sound as an input, and generate new sound as an output – it translates incoming audio into a set of synthesis parameters that are used to generate back the sound.

This is based on two separate processes:

• Encoding process : where a given parameter of inputed audio is transformed into a set a latent variables (128 parameters in general).

• Decoding process: inverts these 128 latent variables back into sound.

As each model is trained on a limited set of data, it will try to extract the parameters even if the input sound does not match the original database. This is why RAVE is able to perform timbre transfer. For example, if RAVE has been trained on piano sounds, and is then given a violin sound, it will try to extract synthesis parameters from it and generate it as a piano sound. This allows you to use RAVE as an audio effect through transforming incoming audio, but also as a synthesiser – by directly controlling these latent parameters.

I discovered RAVE through Michael at the LCC Creative Technology Hub and as soon as he mentioned it I recognised the importance of RAVE for myself in this project. It, itself is an AI tool that artists are using to create generative sonic work, with a strong community surrounding the tool, this is a great example of subcultures forming around AI.

RAVE can be seen as a more ethical AI alternative because it’s architectural design, giving you, the user, control over the data being inputed for the generative output. Artists providing sources are able to consent to the use of their audio, therefore if you train it on your own recordings or licensed datasets, it avoids the ‘theft’ concerns often associated with AI tools using the internet.

Because it is used more as a creative instrument rather than a replacement for human labor, the perspective of it being an AI tool is different to, say, how large corporations use AI as a tool.

RAVE’s ability to ‘timber transfer’ allows it to be used in a way which many see as a natural progression of digital music.

Like all deep learning models, training RAVE requires significant computational power, contributing to carbon emissions and the use of water – a common environmental concern for all generative AI. It is hard to say if or how this would change as I feel I currently do not know enough about the environmental impact of these supercomputers which are powering AI. I fully comprehend and empathise with the refusal to use AI due to the environmental damage it has. However, there are many contributing factors to this destruction of nature, which, in contemporary society is hard to control due to the involvement of advanced technology in our everyday lives. This is an aspect of AI that contributes hugely to the mass rejection and lack of acceptance to the use of AI in art, therefore is a key aspect that I will be researching for this essay.

RAVE is an facet of AI that I am able to cite for both elements of this project, the essay as well as the composition. It is a key development in my research for understanding the core of my essay, whilst also providing me with an inspiring, new tool which I can use to create my composition work.

With the work I have been doing this past year, (involving Pure data) I have learnt a vast amount as it was an aspect of sound arts I had no prior knowledge of, and so I have built my work from the ground up in that respect. However I found I got to this point with my work, where, I didn’t quite know which direction to take it in. There are a number of routes I am able to take with the knowledge I now acquire, and I feel using RAVE is one I feel motivated to continue in.

I feel it is important to understand the importance of AI in the contemporary artistic world as it is not leaving anytime soon, in fact the opposite. AI will continue to evolve at rapid speeds and in ways that get more complex, therefore being able to comprehend it now feels significant.

With the coding knowledge I have picked up from using Pure data (although tiny compared to others) I feel confident in continuing to learn and use code in a creative way. Inputting my own entire database of audio into RAVE to then use to create work feels very exciting to me, and is a continuous project that will really allow me to understand both RAVE itself and how AI learns and uses sources to create generative sounds.

Some examples of artists using RAVE:

(ESSAY RESEARCH)

I came across the term recuperation in Dick Hebdige’s book: ‘Subculture; The Meaning of Style’, most prominently in chapter 6, ‘The Unnatural Break’. In media, sociology, and critical theory, recuperation refers to the process of radical, subversive, or counter – cultural ideas & styles being co-opted, absorbed, and commodified by mainstream media and capitalist culture.

Hebdige describes the process of recuperation having two characteristic forms :

1. Commodity form = The conversion of subcultural signs (dress, music, etc) into mass produced objects.
2. Ideological form = The labelling and re-definition of deviant behaviour by dominant groups – the police, the media, the judiciary.

The capitalist system integrates potentially subversive elements into its own structure, therefore neutralising the revolutionary potential through commodification and exposure through their outlets. It’s a level of control that establishments have over their audience, whether they’re conscious of it or not.

It is through recuperation that the context and meaning of a work is stripped away, severing the emotional affiliation of the environment it once inhabited. Now perceived for its profit, the reasoning behind the work becomes redundant, leaving a kind of soulless atmosphere to the now ‘product’. An occurrence that is repeated throughout history, the industrial foundations of the art world thrive on the process of recuperation, requiring a level of skill and creativity that runs primarily through subcultures.

“The diffusion of youth styles from the subcultures to the fashion market is not simply a ‘cultural process’, but a real network or infrastructure of new kinds of commercial and economic institutions.” John Clarke (1976b).

Social Hieroglyphs.

Coined by Karl Marx, social hieroglyphs refer to the concept where, commodities hide the social interactions of a production beneath a surface of exchange value. As a consumer society we view an object or a creation, predominately seeing its profitable value and use, while the story behind it, the sweat, the struggle, becomes a hidden language we can no longer read.

The term comes from Egyptian hieroglyphs, where pictorial documentation required decoding to reveal a hidden language of human thoughts, history, and interactions. They represent the connections between people rather than just between things.

Marx’s emphasis on the term was about acknowledging and decoding what is put in front of us in contemporary society, understanding the human effort put into the products we consume. Underneath the surface lies a physical map of the human labor. This understanding becomes crucial in empathising with other people, creating meaningful connections and changing our perspective on commercialisation.

Art often evolves from a struggle, whether that be on a mass scale or an incredibly personal level, it is used as an expression, a way of processing intense emotion in a constructive, impactful way. However, recuperation transforms a radical concept into a social hieroglyph, thereby masking the very labor and struggle it once emerged from.

In a usual interaction between a person and a piece of artwork (be that music, painting, writing , etc) a huge part of its value lies between the relationship you form emotionally with the work, based off your own personal experiences and the original intent of the artist. You therefore become aware of the exertion put into the piece, and are able to sympathise with the artist and the community that forms around the work.

However, this kind of relationship is often lost through art entering the commercial world, it becomes a commodity in which both the art and the artist discard the original intentions in exchange for profitable value.

This is where recuperation has the biggest impact socially, it has the ability to break down communities and control certain people’s perceptions on a mass scale. Through the absorption of once radical concepts mainstream industries widen an audience (which can be positive), however when context gets lost to such a large extent, and money is at the forefront of the work, these ‘hieroglyphs’ make it so the consumer sees only a finished, polished product. Deeper thought is not required.

However, regardless of this mainstream reconstruction, subcultures are constantly moving and growing, creating an undercurrent of change that is equally impactful, just to a different collection of people.

(ESSAY RESEARCH)

In order to understand the pattern that radical concepts move through, it is crucial to realise and appreciate the significance that subcultures have in that process.

Subculture is defined as ‘the behaviours, beliefs, or practices of a particular group of people within a society that differ from those of the majority or dominant culture.’ (Oxford Dictionary). Based on shared interests, lifestyles, principles, or characteristics, subcultures provide a sense of belonging to their members, surrounding them with like-minded people.

Throughout the evolution of our society, subcultures have always existed. Focusing specifically on art and media, the realm of a subculture will always inhabit others who are inspired, influenced and interested in the work circulating, therefore forming a community. These communities are the foundations of a subculture, allowing messages and concepts to flow under the mainstream current of beliefs. They allow for freedom of expression, in a distinctly important way.

The value of a subculture lies within the people, not the profit.

As previously mentioned, Dick Hebdige’s book: ‘Subculture; The Meaning of Style’ has been a rich source used for understanding the relationship between subcultures and mainstream cultures. Not only has it widened my knowledge on the significance of subcultures but it has expanded my perception on art, media and styles as a commodity. Hebdige analyses the movements of counterculture throughout contemporary history, recognising the pattern of commodifying a once ‘extremist, radical’ concept.

Though generally more critical of the “loss of soul” that occurs when a subculture is tamed through entering the corporate world, Hebdige does acknowledge that the act of recuperation allows radical ideas to reach a wider audience, although no longer deeming it as a radical idea. It shifts the “cultural needle” even if the original subculture and their intent is sacrificed in the process. This shift is often crucial for the evolution of our understanding on people and lifestyle. To a certain extent, this whole process seems inevitable, therefore it feels important to at least recognise a positive effect that recuperation can have. (Although I am not in support of it).

Subcultures rely on a purposeful search, they aren’t fed to you, you have to actively seek to find your specific community within the undercurrent.

There are prominent examples of a subculture piercing through into mainstream, for both positive and negative reasons, the exposure of a different way of thought is often the catalyst for societal change.

‘Teddy boy’

Teddy boys and girls, or simply ‘Teds’, marked the arrival of the most distinctive post-war youth style of 1950s Britain. Emerging through working class teenagers who defied austerity with fashion and music. They wore long drape jackets and drainpipe trousers, often interpreted as a reversion to Edwardian fashion, hence the name Ted – The term ‘Teddy boy’ was originally coined by the popular press in 1953, and derived from the word ‘Ted’ being commonly used as a shortened alternative for the name ‘Edward’.

Inspired by a more American life, Chicago Gangster and zootsuit styles were a huge influence on the fashion and conducts of a Teddy boy. In Britain, these specific styles became associated with the ‘spivs’, the cockney boys who dealt in the black market of the 1940s, often deviant and violent- much like the Teds (through the eyes of the media).

More than just a style, Teds had symbolic significance. They represented a radical break from the post-war frugality and class rigidities, rejecting the societal expectations that Britain conformed to. By reinstating the Edwardian styles, which were originally marketed towards young upper class men through high end Savile Row tailors, these working class youth asserted a new sense of pride and social visibility.

Teddy boys also became a symbolic focus for the social anxieties that the changes of post-war Britain provoked. Through the eyes of many, they were seen as both the perpetrators of a new wave of violent crime, and, as a benchmark of the nation’s wider, traditional cultural dissipating.

Punk

British punk emerged in 1976, driven by bands like the Sex Pistols and The Clash, Punk spread throughout the suburbs, provinces and cities of the UK. Characterised by clothes designed by Malcolm McLaren and Vivienne Westwood, with their Kings Road shop ‘SEX’, they forged an aesthetic of rips, fractures and tensions, capturing the mood of the time. Punk informed everything from music through to design, fashion, artwork, writing and performance. It served as the voice of expression for the youth generation that felt increasingly alienated by the stagnant social and economic life of the late 1970s.

“To act took precedence over receiving/consuming.”

Punk was seen to reload and rejuvenate youth culture as a place of freedom, provocative fun, protest and imagination. 

However, almost immediately, punk proved a contested cultural space, a site of resistance that was simultaneously under siege by the forces of the media. After Sex Pistols’ ‘foul-mouthed’ appearance on teatime television in December 1976, moral panic ensured punk moved overground into the wider public consciousness. 

As time went on Punk did survive, often trying to leave the presence of the ‘establishment’, however struggling to. Through the exposure, Punk lost its once revolutionary, extremist value through commodification. The artefacts of punk, the safety pins, the distorted chords, the DIY aspects were quickly identified by the “infrastructure of commercial institutions” as valuable trends.

Rave Culture

British rave culture emerged in the late 1980s, exploding with the in 1988-1989, “Second Summer of Love”, with the rise of Acid House sparking the phenomenon. Initially occurring in the warehouse parties of London, rave culture grew fast and soon spread to locations all over the country, occurring in large abandoned industrial areas or in open countryside landscapes. London warehouse parties, along with pirate radio and the introduction of ecstasy established the scene of rave culture.

The synergy of house music and ecstasy catalysed a dance movement that broke the pretentiousness of the existing UK club scene. The relationship between the music and the effects of MDMA made for a loving intensity of liberty within the dance and party world. It was a DIY movement that thrived on building, not buying (much like most subcultures).

 The UK scene was initially dependent on tracks from Chicago, Detroit and New York, but soon began to develop its own rich forms of house and techno. Rave culture brought about a significant, and often controversial, shift in UK youth culture, creating a new youth movement that left a lasting impression on British society. It allowed for a space of communication that was open and fuelled by passion, inspiration, connection and dance. An impression that is still very relevant today, having changed our approach to dance music.

Berlin-based artist duo, Holly Herndon & Mat Dryhurst are at the forefront of the intersection between music, artificial intelligence, and decentralised technology. Herndon holds a doctorate from Stanford University’s Center for Computer Research in Music and Acoustics (CCRMA), she is renowned for her vocal-driven electronic music. Dryhurst is a theorist and artist whose work focuses on the social and economic structures that support creative labor.

Together, they have pioneered the concept of ‘Data Dignity’, rather than viewing AI as a tool for automation or the extraction of subcultural data, they treat it as a collaborative medium. 

Holly+

In 2021 Herdon and Dryhurst released Holly+, a digital copy of Holly Herdons voice. Using machine learning, the model allows users to upload a polyphonic audio file and have it sung back in Herndon’s own vocal timbre. They encouraged anyone to create new work with her AI voice, as part of an expansive art and research project experimenting with the economy around her digital likeness.

After the initial release of the voice, there have since been more instruments made, allowing for people to upload scores for her voice to sing, also allowing for people to perform in her voice in real time. (premiered at Sonar 2021) These instruments have been created in a joint collaboration between Herndon Dryhurst Studio, Never Before Heard Sounds (NYC), and Voctro Labs (Barcelona).

Holly+ functioned as both an instrument and a radical experiment in decentralised intellectual property. Governed by a DAO (Decentralised Autonomous Organisation), ensuring that the use of her digital identity is ethically managed, with a portion of the profits from any approved works returning to the original creator and the community.

Holly+ challenges common pessimistic perspectives around ‘deepfakes’ (synthetic media; images, audio, or video, generated by artificial intelligence to deceptively swap faces, manipulate voices, or create realistic, fabricated scenarios of real people). Being quite an early piece of work centred around AI, in regards to its evolution, Holly+ holds a strong president for how artists can reclaim agency within an automated landscape. Something, which continues to become a more relevant and striking threat to artists. It stands as a foundation for the ethical integration of machine learning, shifting the narrative from one of displacement to one of augmented expression.

Holly+ is part of an evolving lineage of AI vocal projects created by Herndon and Dryhurst, creating a kind of digital ecosystem of artwork and data, focusing on the sovereignty of the individual and the collective.

‘The Call’

“We are trying to position AI as a monumental collective accomplishment and coordination technology, part of a lineage that goes back to group singing rituals that predate language, and religious protocols that emphasise participation in something greater than the sum of its parts. We feel this is a more interesting framework for approaching the subject and can also be instructive for policy moving forward. AI is just us, in aggregate- it is beautiful and requires rethinking how we arrange life.”

The Call (2024) is a large-scale project composed from the voices of fifteen diverse choirs from around the UK, ranging from traditional church groups to experimental vocal ensembles. The recordings were then used to train a custom AI model that simulates a collective vocal identity. When an individual interacts with The Call, they are performing through a digital representation of a community.

The Call centres on developing new protocols and materials for the creation and adaptations of musical of AI models. To train the AI model, Herndon and Dryhurst composed a songbook of hymns, singing exercises and a recording protocol. The singers are now part of a data trust experiment that allows for the distribution of power between the contributors to the training data and those who use the models.

First exhibited in The Serpentine Gallery (2024-25), The Call was an immersive and interactive spatial audio installation, the physical architecture designed to evoke the sacred and communal history of human sound. The work is centred around the large, wooden structure often referred to as the ‘Hearth’ (seen in the above picture). The Hearth simultaneously looks a high tech piece of modern equipment as well as an ancient, traditional kind of ritualistic altar. Inside the structure are over 120 GPU fans that are tune to be able to perform music, as you walk around it, the AI-generated voices of the fifteen choirs move with and around you.

Along with the Hearth there were several other structures, each coinciding with the spiritual, renaissance-like appearance of the work. Each structure performed in a different way and each represented a particular aspect of the project.

For example in once room was a huge chandelier looking object, a dense, high-tech rig that represents the recording protocol used to capture the fifteen choirs. (Each choir was recorded with a microphone in the centre of a spherical surrounding of singers.) This object is called the Wheel and when you step in the room you hear every one of the 15 choir groups singing as if they’re in the room with you.

The Call offers us a rejuvenated perspective on the collective nature of human creation through the technological tools of the 21st century.

When I discovered Herdon and Dryhursts work, I instantly felt inspired, their use of integration with AI felt refreshing and captivating. Ethically, they are encouraging a demand for change within the way artists and their work are treated in relation to AI. It is clear they understood from early on the ownership issues that would arise with the use of AI and with that knowledge they have been able to create morally conscious works of art.

In regards to where my practice sits in relation to artists like Herdon and Dryhurst, who are using AI as a tool, is something I am still understanding and developing.

This project marks the first time I have incorporated AI within my practice. It is, if I am being honest, a concept that has intimidated me due to both the power and extent of it, as well as the public response I have seen to other practitioners using AI to create artwork. I have been exposed to, and aware of, a predominantly negative reaction to creative the use of AI and therefore didn’t necessarily want to engage in the controversial act of using AI.

I am aware of why people revolt against the use of it, I don’t agree with many of the approaches and ways that people engage with AI. However I do think it is important to acknowledge the strong communities of practitioners who have formed around the innovative involvement with AI, using it as an artistic tool to create and inspire.

I find it necessary to do so as AI is not going to be leaving our society anytime soon, I think it is better to embrace than shun an aspect of modern technology that has the potential to be so incredibly damaging to our civilisation. AI learns from human input, meaning in order to shape a rounded tool, versatile for all kinds of use, it requires an input from the imaginative, empathetic and artistically unique brains. Of course this does not mean you should forget about the lasting ethical and environmental impacts of AI, keep that consciousness and sensibility, but also understand that there is a cruciality in creative engagement. This is how my mindset has been shaped since researching for this project, although be it, a perspective that remains controversial.

Through finding artists and communities who are using AI in an ethically and environmentally conscious way, it has allowed me to understand how and why I am going to engage with it myself, finding inspiration from the many other artists online who I have found to be using AI and RAVE in captivating ways.

When connecting my essay and research work to the practical sound piece, my focus was set on the relationship between the ethical approaches to using AI and the subcultures this it sits in. RAVE enabled the foundations of this work, allowing me to create a piece that accesses a morally correct manner of using AI creatively, directly through the artists that inhabit said subcultural communities.

Originally I wanted to use RAVE to build my own data set which I would then use to compose the piece, however I soon realised this was overly ambitious of me in regards to the time frame of the project. In order to build a densely rich model you need to provide between 2-10 hours of recordings which does require some time. In order to combat this issue I found that the designers of RAVE actually made a version that can be put into a DAW and so this what I used to create the piece. The plug in itself came with 10 pre loaded RAVE models which I began exploring, however I wasn’t fully satisfied with the sounds they were producing. Therefore I decided to download other models that artists and designers had made, (see Process of Making blog for context) which I felt to be much more inspiring.

Through using these models within the DAW, I felt it representable in relation to the ethical concerns of using AI. The sources I used were ethically collected, directly from the artist to the users, their full consent has been given, therefore the ownership complications, that are so common within AI, are taken away.

Environmentally, regardless of the purpose, using AI does negatively impact the world, large scale data centres are what power our ability to use AI. And so using RAVE may be more ethically liable but does still have contradictable aspects to its operation. However, while a model like ChatGPT requires thousands of high power GPUs running for months, a RAVE model is designed to be efficient. It can often be trained on a single high end personal computer in a matter of hours or days.

Alongside the creative use of AI, my essay focuses on the importance of subcultural communities, and their impact on perspective. In order to connect this to my practical piece, I decided to use the sources of subcultures I found during my research.

IRCAM was a massive contributor to this, providing a space where practitioners are able to share and discuss current works in a welcoming, sympathetic environment. I wanted to have this association of subculture in my piece to tie it to the written work, but also to create a practice that builds on the sense of belonging that these communal spaces offer. I feel that from this project I have widened my knowledge and passion to create, realising these specific subcultural spaces are very attractive to me. Although this may not be made apparent to the listener, the connection is there, helping to create continuity to the work as a whole.

I used multiple sources from these communities, free and open to all, as well as reading and learning about the process of building a RAVE model. This information was not only useful for this specific project, but for my own personal practice as I eventually do want to build my own model.

https://forum.ircam.fr/search/?topics=RAVE%20Model%20Challenge%202025

Within this process of making I wanted to create a work that represents my current practice, something I can use to grow and adapt. From my period of research I acquired a lot of new knowledge on the topic of AI, and the practitioners working with it, and begin questioning why I was intrigued into their work. What parts of it attracted and inspired me? I took this inquisitive element and kept it relevant during the making of my piece, relating elements of my work to the factors of others that influenced me. Although this may not be noticeable to others, it has allowed me to delve deeper into the specifics of where I want to take this work, and how I can include components of previous projects with this to create a new, relevant practice for myself.

In my week 26 lecture with Kate Carr, she was showing us some examples of artist performance models in different contexts, one of these examples was Pamela Z’s ‘Breathing’. I was not previously aware of Pamela Z’s work, however when shown this video I found an instant attraction, mostly toward her techniques of working with controllers to manipulate the sound through physical movements. This is something I would like to explore and work with, and I feel it leads on well from the work I have been doing with code.

“Pamela Z (b 1956) is a composer/performer and media artist working with voice, live electronic processing, sampled sound, and video. A pioneer of live digital looping techniques, she processes her voice in real time to create dense, complex sonic layers. Her solo works combine experimental extended vocal techniques, operatic bel canto, found objects, text, and sampled concrète sounds. She uses MAX MSP and Isadora software on a MacBook Pro along with custom MIDI controllers that allow her to manipulate sound and image with physical gestures.”

The use of voice in Pamela’s work is prominent, the relationship between voice and body is a sophisticated relationship, with the movement of each effecting the other. The audible aspects of her performance are beautifully layered and engage your brain in a fascinating way. Visually, her performance move through the motions of her body, which are commonly controlling the multiple layers of sound. Compared to other performance artists, Pamela’s stages are relatively empty, often times she has the limited entities of; herself, her laptop and the microphone, drawing your focus to the organic, natural elements of her work.

Performance art is something I can be quite picky about, I have seen a lot of sound & visual art practitioners who’s performances don’t intrigue me. I find that in performance there is a kind of stretch to be the most unconventionally ambitious, and often times this takes away from the curiosity and charm that a good performance artist can have. Obviously, this is subjective, and I have seen a large number of performance artists of whom I think are wonderful and inspiring, Pamela Z being one of them.

This physical form of sonic manipulation is an aspect of working with technicalities that I am yet to achieve, simply due to my lack of knowledge. As I am relatively new to working with elements like; electronics, coding, computer software, etc, there is a lot of information and understanding that I have not yet learnt. I am however eager and very willing to learn it, and the opportunities this provokes excites me a lot. I see artists like Pamela Z or Holly Herdon who are working with tech in a very innovative way, and it inspires me to carry on producing work.

The use of controlling sound and visuals through physical gestures is something that ties in heavily with Touch Designer, specifically through mapping and body tracking. As this is something I am very intrigued by, and eager to understand, I feel that my aspirations of where I want my work to go is cohesive with my skills. It is through researching and observing artists and practitioners work that has inspired me to learn software like Touch Designer or RAVE. And although I only have a basic level of knowledge and capabilities, I am eager to continue growing this understanding.

As I have mentioned before, working with AI as a tool in my practice is an entirely new concept to me. It is an aspect technical work that I am not familiar with, however since starting this project I have been able to gather a basic understanding of how existing practitioners are engaging with AI creatively, within a conscious format.

Leading up to this project I have been continually more interested in working with specialised technical elements, creating both visual and sonic work through these applications.

Through using PureData and beginning to learn other software such as Arduino, I find myself more and more excited and inspired to create work within these realms. Because of this, I am not surprised that the production of both sonic and visual work using AI interests me. The knowledge, and the people, that circulate both the technical software and the AI-driven domains are interdisciplinary and often correspond between the two. Meaning, there is a widespread community of practitioners to learn and communicate with.

The expansive potential of working with AI as a tool and other digitally based programmes is both stimulating and slightly formidable, there are so many ways in which you can use them, I find I often get lost in the possibilities. This is something, I will say, that this project has helped improve, through looking at other practitioners I feel more directed in ways I would like to work, and what I want to achieve from doing so.

I am able to envision many ways in which I can expand upon on previous projects and begin new ones, intertwining new and old skills. I want to use the knowledge I have gained from this project to begin working on a piece that is both visually and sonically exciting. Although I have been focused on sonic practices for this project, I also want to widen my knowledge on visual aspects, looking at artists who are using technology to create original, innovative visual works. This is something I am definitely more aware of, without having to look as deep, I know of practitioners working in this way as they appear to me more through networks of social media. Instagram especially, informs me about new artists as their short video works appear on my feed regularly. I find this to be huge inspiration due the eclectic exposure of visual media I see daily.

Here are a couple of examples:

https://www.instagram.com/reel/DYEtR_fMa-4/?utm_source=ig_web_copy_link&igsh=MzRlODBiNWFlZA==

https://www.instagram.com/reel/DXlOn-rCNLX/utm_source=ig_web_copy_link&igsh=MzRlODBiNWFlZA==

https://www.instagram.com/reel/DRgeEQ4kRAF/?utm_source=ig_web_copy_link&igsh=MzRlODBiNWFlZA==

Recently I have also begun teaching myself Touch Designer and I think this is a great gateway into combining both my visual and sonic works together. It gives me a platform to use both elements as the centre piece in an immersive way, therefore really engaging my new found interests. As I begin to take this further, I am able to envision ways in which all the independent elements of my passions come together, and I feel enthusiast about my work to come.

Below are 10 RAVE models that the plug in initially came with, as I have mentioned in a previous blog, I didn’t find these models to be particularly exciting for the kinds of sounds I wanted to make. Although, I will say, they still produced very interesting and intriguing noises, built from a diverse set of sources. They were useful in helping me understand both how the plug in works and the parameters in which you have control over.

After realising I wanted to explore further into other models I began looking online, I found Ircam forums to be the best source of finding them. The link below is where I retrieved the ones I used from:

https://forum.ircam.fr/search/?topics=RAVE%20Model%20Challenge%202025

From this page I began looking into the published models that were put forward for the Rave model challenge 2025, from the many to look through, there were a few that sounded most interesting to me. I was attracted to the original source of sounds that the data sets were built off and from this I chose to use these main three:

Schizophrenia.ts – Zhao Jiajing and Bryan Yueshen Wu

I actually found the concept of this model to be more exciting than the sounds it produced, although I did like the tone and the noises it was generating, I was attracted more to the model because of its data content. I thought using an amalgamation of audio from youtube shorts was such an interesting notion, very relevant of contemporary times.

The audible businesses of social media has become extremely normalised, and that has happened very quickly, it is something that is incredibly unnatural, our brains are processing audio at a speed it is not used to. Therefore I thought by combining this with AI, it creates this incredibly synthetic concept of work, rich with context, meaning and significance, this is the aspect of the model that inspired me.

Black Latents – Martin Heinze 

“Types of sounds used: Full length audio tracks from Black Plastics, a seven-part release series comprising a total of 28 electronic music tracks by the artist Martsman, mapping a sonic landscape oscillating between Experimental Techno, Breakbeats, and Drum & Bass.

Total duration of audio corpus used for training: Approximately 3h

Artistic intention: Extract dominant characteristics from a defined body of musical work and use the trained model to respawn new audio material.”

This model was the winner of the challenge and it was apparent that this was a much more musically trained set, made to sound more rhythmically inclined, despite the fact that these models don’t really have a rhythm to them because of the randomisation and latent noise of AI. It did however have more distinct sounds which acted as a more solid foundation to the noise of the model (compared to the others which feel looser and more flighty).

086-jaap-3.5m-noisefloor – Jaap Blonk

“This RAVE model is trained on a dataset of Jaap Blonkʼs vocal performances. The dataset was recorded by Blonk with Jonathan Reus specifically for training models as part of Reusʼs Dadasets project, in particular for text-to-voice synthesis in Reus and Victor Shepardsonʼs Tungnaá instrument.
The dataset totals about 100 minutes of close-mic recordings of Blonkʼs solo voice performances, which are a mix of scored and improvised.”

I was attracted to this model due to the fact it was trained on vocals, not instruments, I became intrigued into how it would react to other vocals being inputed through the model. I knew I wanted to work with my voice for this piece as I wanted to create this kind of natural vs unnatural element to the work, and so when I found this model, I thought it was fitting to my themes.

At the time of writing this I have not yet experimented with inputting my voice through this model, so I am currently unsure of how it will sound but I am intrigued to see if it will have an interesting effect.

When it came to the production of the creative work I knew that I wanted to use my voice as the main source of sound in the piece, using the RAVE models to then manipulate and orchestrate it. I wanted to include vocals to have this contrast of human and machine, on one side is this completely natural element with no integration of synthetic noise, and on the other is an artificially machine-made ‘voice’ adding the unnatural element to the work.

When beginning the process of making this piece, I definitely struggled at first to find the direction I wanted to take the work in. I was confident in using my voice but when I initially tried to record, I felt lost and unsure on how to use RAVE alongside my voice effectively. This led to prioritising the other aspects of the project over the composition and dedicating more of my attention to the written work. This is a process that is common for me, I usually complete the practical aspect once the writing is complete as, I feel the knowledge I learn from the research is needed to provide context to the practical piece. Although this structure does work well for me, in this case I think I should have provided more time to focus on the sound work.

One problem that repeatedly occurred during this project was Logic crashing due to the processing size needed for RAVE to run. I had multiple tracks using RAVE models at the same time, and even when increasing the buffer size on Logic, it would still overload the system and constantly crash. This became very annoying and off-putting to using RAVE. In order to combat this issue I realised I needed to use RAVE in increments, muting it on playback, and turning down the volume of every track that had it on when not playing, this also eliminated any latent noise that the models were outputting. This did help, however did not solve the issue entirely, and I still faced many issues with a ‘system overload’, having to close Logic and reopen it many times to restart it. In the end I was able to use RAVE on all the tracks I wanted, producing the desired effect. However, in order to export it I had to bounce it offline as when trying to bounce in realtime it started to make some glitchy sounds that were not in the piece – this was from the overload of RAVE.

Next time, in order to combat this issue, I would try and use a computer that has more processing power, defining what it is I want to make from an early stage, and how to best use the abilities of theAI models.

All that being said, I was actually quite pleased with the final outcome of the practical work. I kept to my original plan of using only my voice as the input, with no other instruments or synths being used to create the audio. I felt very happy about this aspect as like I said, I initially felt unsure of how to execute the unaccompanied use of my voice.

I used the QuickSampler in Logic to input my voice and delegate keys to certain letters, words and phrases, meaning I was able to form sentences using the keyboard. Using a sampler within a DAW is something I am previously familiar with as I find working with samples in this way inspiring. However, using my own voice and slicing the the sample up to this extent was something new to me. This whole process of using just my voice was very interesting as I had to break down the understandings I had on making a composition and look at the production from a different perspective. I am very happy with the outcome as it is very different to previous works I have made using samplers, and it has inspired me to continue creating, using both my voice and other RAVE models.

Taking inspiration from the artists I had researched, like Pamela Z, Herdon, and Dryhurst, whose work uses voice through the manipulation of technology, I feel this piece reflects the work of my essay well. It includes the elemental aspects of human and machine, whilst being an ethically viable use of AI. Both Pamela and Herdon use voice to build a united relationship between human and machine and this is what drew me to their work. Therefore, I feel it is right to have made a piece of work that does the same, from my own interpretation of the subject matter.

I used the RAVE models to create a kind of background atmosphere to the piece, and in fact, without RAVE this work would be rather empty. But that was the whole point, I viewed the noises the models produced as the other instrument of this work, accompanying my voice and at times taking on the voice.

The control I had over the models was an interesting aspect of this project, through inputting my voice and having the ability to manage certain parameters like the wet to dry signal, I was able to manipulate the movements of the sounds. However, the specific noises that the models created was out of my control, deriving from the data set in a semi randomised format. This made it fun to work with as it was like having another entirely independent input, except one that I did have some levels of control over. This did however also at times become tricky as I wanted the models to produce certain sounds that it just wouldn’t, I then realised I had to let go of the orchestrating aspect to the AI and let it run freely, which in turn ended up sounding very intriguing, as I made something I couldn’t.

Overall, I am pleased with the final outcome of this project, I feel both element 1 + 2 are cohesive with each other and give context the thematic points of the work. The use of RAVE has inspired me to continue making work with AI in ethical ways, and I now want to build my own model through knowing how they operate in a DAW. I feel I have made a sonically deep piece of work that explores both the themes of my research as well as my personal interests, making this specific practice influential in where I plan to take my work next.