Digital Culture & AudioVisual Challenges

This practice-based research explores the innovative fusion of technology, art, and sound, focusing on the potential of sound to drive the creation and manipulation of printed images. Central to this investigation is using artificial intelligence (AI) text-to-image generation as a groundbreaking idea matrix for contemporary printmaking. By leveraging the power of AI algorithms, the research challenges traditional notions of image creation and representation, opening up new avenues for artistic expression and conceptual exploration.

The AI text-to-image generation process serves as a digital idea matrix, enabling the creation of unique, complex, and often surprising visual forms based on textual input. This approach offers a novel way of conceptualising the relationship between language and visual representation, as the AI algorithms interpret and translate written concepts into intricate, multi-layered visual compositions. The resulting AI-generated images become the foundation for the subsequent stages of the printmaking process, replacing traditional sketches, drawings, or photographic references as the starting point for artistic creation.

As the research progresses from the AI-generated idea matrix to the subsequent stages of sound-driven, post-digital printmaking, the integration of AI technology remains critical. The AI-generated images serve as the visual foundation for the laser-etched PVC plates, which generate the sound data that drives the manipulation of the projected images. This complex interplay between AI, sound, and post-digital printmaking techniques highlights the innovative potential of integrating cutting-edge technologies into traditional art-making practices.

Integrating AI text-to-image generation as an idea matrix represents a significant shift in how artists conceptualise, develop, and execute their creative ideas. By embracing this technology, the research challenges established notions of authorship, originality, and artistic control as AI algorithms become collaborative partners in image-making. The artist's role evolves from being the sole creator to being a curator, editor, and interpreter of the AI-generated visual material.

The process begins with creating a vinyl record-shaped PVC plate etched with visual information using laser etching techniques. When played on a turntable, this PVC plate generates unique sound patterns based on the engraved visual data. The sound generated is fed into a computer program, such as MaxMsp, via an audio input. The MaxMsp patch analyses the incoming sound data and extracts relevant parameters such as pitch, frequency, amplitude, and rhythm.

These sound parameters are then mapped to specific visual attributes of the projected image, such as shape, size, colour, or position. As the sound plays, the MaxMsp patch continuously processes the audio input and translates the changes in sound into corresponding visual changes in the projected image. For instance, a higher pitch elongates the image while a lower pitch compresses it. The amplitude of the sound might control the size or brightness, with louder sounds resulting in more extensive or brighter visuals. The rhythm could dictate the speed or pattern of movement within the projected image.

By establishing these mappings between sound parameters and visual attributes, the research enables sound data to act as a driving force for the movement and transformation of projected images. The visual composition evolves dynamically in response to the changing sonic landscape, creating a synesthetic experience that merges auditory and visual elements.

This approach to sound-driven visual manipulation pushes the boundaries of traditional printmaking by introducing a temporal dimension and real-time interactivity. The resulting artworks are not static prints but dynamic, audio-visual performances that engage the audience on multiple sensory levels.

The research highlights how technology changes art-making, bridging the gap between traditional techniques and digital innovations. Using AI technology and sound-responsive moving images, the aim is to create artworks that engage audiences visually and aurally, challenging them to reflect on the role of science and technology in art and our lives.

In conclusion, this practice-based research explores the possibility of departing from traditional printmaking methods by utilising sound elements instead of ink and projectors instead of paper. The functionality of the turntable and computer program is similar to that of a printer. However, unlike traditional printing on paper, the printing of sound artworks will be projected, and the visual structure of the projected images will change in real time according to the pitch and frequency of the sound. This research pushes the boundaries of printmaking, merging traditional techniques with innovative digital technologies and sound elements to create unique, engaging artworks that challenge viewers' perceptions.