arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.09448cs.SDcs.AI
收藏

一个提示,多种声音:在基于大语言模型的均衡中建模听众差异

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

Bang & Olufsen A/S, Struer, Denmark(丹麦Bang & Olufsen A/S公司,Struer);Department of Electronic Systems, Aalborg University(奥胡斯大学电子系统系);Pioneer Centre for AI, Copenhagen, Denmark(哥本哈根先锋人工智能中心)

Ioannis Stylianou, Jon Francombe, Pablo Martinez-Nuevo, Sven Ewan Shepstone, Zheng-Hua Tan

AI总结:

本文提出利用大语言模型将自然语言提示映射到均衡设置,通过上下文学习和参数高效微调技术,实现更灵活的音频均衡控制。

摘要:

传统音频均衡是一个静态过程,需要手动和繁琐的调整以适应变化的听觉环境(例如情绪、位置或社交场合)。在本文中,我们介绍了一种基于大语言模型(LLM)的替代方法,将自然语言文本提示映射到均衡设置。这使声音系统控制变得像对话一样。通过利用从受控听觉实验中收集的数据,我们的模型利用上下文学习和参数高效微调技术,可靠地对齐大众偏好的均衡设置。我们的评估方法利用分布度量来捕捉用户多样化的偏好,显示出在分布对齐方面比随机采样和静态预设基线有统计学显著的改进。这些结果表明,大语言模型可以作为“人工均衡器”,有助于开发更可访问、情境感知和专家级音频调节方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑