One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization

TL;DR

This paper presents an LLM-based method for natural language control of audio equalization, enabling adaptive, conversational sound tuning that aligns with user preferences and context.

Contribution

It introduces a novel LLM-driven approach for flexible, natural language audio equalization, leveraging data-driven fine-tuning and distributional metrics for preference alignment.

Findings

Statistically significant improvement in preference alignment over baselines

Models reliably match population-preferred equalization settings

Demonstrates feasibility of conversational sound system control

Abstract

Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.g., mood, location, or social setting). In this paper, we introduce a Large Language Model (LLM)-based alternative that maps natural language text prompts to equalization settings. This enables a conversational approach to sound system control. By utilizing data collected from a controlled listening experiment, our models exploit in-context learning and parameter-efficient fine-tuning techniques to reliably align with population-preferred equalization settings. Our evaluation methods, which leverage distributional metrics that capture users' varied preferences, show statistically significant improvements in distributional alignment over random sampling and static preset baselines. These results indicate that LLMs could function as "artificial equalizers," contributing to the development of more accessible, context-aware, and expert-level audio tuning methods.