Population-Aligned Audio Reproduction With LLM-Based Equalizers

2026-01-14

AI Summary

This work proposes a novel approach to audio equalization by leveraging large language models (LLMs) to enable context-aware, language-driven dynamic tuning, addressing the limitations of traditional manual equalization in adapting to dynamic listening contexts such as shifting emotions or environments. The method integrates in-context learning with parameter-efficient fine-tuning and aligns model outputs with population-level preference distributions using data from controlled listening experiments. Experimental results demonstrate that the proposed system significantly outperforms both random sampling and static preset baselines on distribution alignment metrics, thereby validating the effectiveness and novelty of employing LLMs as “artificial equalizers” capable of interpreting natural language cues to deliver personalized, context-sensitive audio adjustments.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

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.

Problem

• audio equalization
• listening context
• user preference
• adaptive audio
• population-aligned reproduction

Innovation

• LLM-based equalization
• context-aware audio tuning
• in-context learning
• parameter-efficient fine-tuning
• distributional alignment