Table of Contents
Fetching ...

Mixer Metaphors: audio interfaces for non-musical applications

Tace McNamara, Jon McCormack, Maria Teresa Llano

TL;DR

The paper investigates whether musical interface metaphors can enhance interaction with non-musical AI systems, specifically Large Language Models. It introduces the Memetic Mixer, a tangible device using five motorized faders for Big Five personality traits, knobs, presets, and word-tiles to steer LLM behavior. Two week-long ecological studies with six fine-art students compare the mixer against a non-mixer word-tile interface, showing the mixer yields more immediate, embodied control and creative exploration. The work provides a design-metaphor toolkit and argues that cross-sensory metaphors can enrich human-AI interaction and inspire interface designers in other fields.

Abstract

The NIME conference traditionally focuses on interfaces for music and musical expression. In this paper we reverse this tradition to ask, can interfaces developed for music be successfully appropriated to non-musical applications? To help answer this question we designed and developed a new device, which uses interface metaphors borrowed from analogue synthesisers and audio mixing to physically control the intangible aspects of a Large Language Model. We compared two versions of the device, with and without the audio-inspired augmentations, with a group of artists who used each version over a one week period. Our results show that the use of audio-like controls afforded more immediate, direct and embodied control over the LLM, allowing users to creatively experiment and play with the device over its non-mixer counterpart. Our project demonstrates how cross-sensory metaphors can support creative thinking and embodied practice when designing new technological interfaces.

Mixer Metaphors: audio interfaces for non-musical applications

TL;DR

The paper investigates whether musical interface metaphors can enhance interaction with non-musical AI systems, specifically Large Language Models. It introduces the Memetic Mixer, a tangible device using five motorized faders for Big Five personality traits, knobs, presets, and word-tiles to steer LLM behavior. Two week-long ecological studies with six fine-art students compare the mixer against a non-mixer word-tile interface, showing the mixer yields more immediate, embodied control and creative exploration. The work provides a design-metaphor toolkit and argues that cross-sensory metaphors can enrich human-AI interaction and inspire interface designers in other fields.

Abstract

The NIME conference traditionally focuses on interfaces for music and musical expression. In this paper we reverse this tradition to ask, can interfaces developed for music be successfully appropriated to non-musical applications? To help answer this question we designed and developed a new device, which uses interface metaphors borrowed from analogue synthesisers and audio mixing to physically control the intangible aspects of a Large Language Model. We compared two versions of the device, with and without the audio-inspired augmentations, with a group of artists who used each version over a one week period. Our results show that the use of audio-like controls afforded more immediate, direct and embodied control over the LLM, allowing users to creatively experiment and play with the device over its non-mixer counterpart. Our project demonstrates how cross-sensory metaphors can support creative thinking and embodied practice when designing new technological interfaces.

Paper Structure

This paper contains 17 sections, 4 figures, 2 tables.

Figures (4)

  • Figure 1: A Moog Subsequent 37 synthesiser with classic analogue aesthetic (left) and an audio mixer console with knob and fader controls (right).
  • Figure 2: Schematic diagram of the Memetic Mixer.
  • Figure 3: Knobs and their function groupings in the Memetic Mixer
  • Figure 4: The Mimetic Poet (left) a previous design without the use of audio-inspired controls, and the Memetic Mixer (right), a re-imagined version of the Mimetic Poet inspired by audio metaphors.