Can Large Language Models Predict Audio Effects Parameters from Natural Language?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Doh, Seungheon, Koo, Junghyun, Martínez-Ramírez, Marco A., Liao, Wei-Hsiang, Nam, Juhan, Mitsufuji, Yuki
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911061005828096
author Doh, Seungheon
Koo, Junghyun
Martínez-Ramírez, Marco A.
Liao, Wei-Hsiang
Nam, Juhan
Mitsufuji, Yuki
author_facet Doh, Seungheon
Koo, Junghyun
Martínez-Ramírez, Marco A.
Liao, Wei-Hsiang
Nam, Juhan
Mitsufuji, Yuki
contents In music production, manipulating audio effects (Fx) parameters through natural language has the potential to reduce technical barriers for non-experts. We present LLM2Fx, a framework leveraging Large Language Models (LLMs) to predict Fx parameters directly from textual descriptions without requiring task-specific training or fine-tuning. Our approach address the text-to-effect parameter prediction (Text2Fx) task by mapping natural language descriptions to the corresponding Fx parameters for equalization and reverberation. We demonstrate that LLMs can generate Fx parameters in a zero-shot manner that elucidates the relationship between timbre semantics and audio effects in music production. To enhance performance, we introduce three types of in-context examples: audio Digital Signal Processing (DSP) features, DSP function code, and few-shot examples. Our results demonstrate that LLM-based Fx parameter generation outperforms previous optimization approaches, offering competitive performance in translating natural language descriptions to appropriate Fx settings. Furthermore, LLMs can serve as text-driven interfaces for audio production, paving the way for more intuitive and accessible music production tools.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20770
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can Large Language Models Predict Audio Effects Parameters from Natural Language?
Doh, Seungheon
Koo, Junghyun
Martínez-Ramírez, Marco A.
Liao, Wei-Hsiang
Nam, Juhan
Mitsufuji, Yuki
Sound
Multimedia
Audio and Speech Processing
In music production, manipulating audio effects (Fx) parameters through natural language has the potential to reduce technical barriers for non-experts. We present LLM2Fx, a framework leveraging Large Language Models (LLMs) to predict Fx parameters directly from textual descriptions without requiring task-specific training or fine-tuning. Our approach address the text-to-effect parameter prediction (Text2Fx) task by mapping natural language descriptions to the corresponding Fx parameters for equalization and reverberation. We demonstrate that LLMs can generate Fx parameters in a zero-shot manner that elucidates the relationship between timbre semantics and audio effects in music production. To enhance performance, we introduce three types of in-context examples: audio Digital Signal Processing (DSP) features, DSP function code, and few-shot examples. Our results demonstrate that LLM-based Fx parameter generation outperforms previous optimization approaches, offering competitive performance in translating natural language descriptions to appropriate Fx settings. Furthermore, LLMs can serve as text-driven interfaces for audio production, paving the way for more intuitive and accessible music production tools.
title Can Large Language Models Predict Audio Effects Parameters from Natural Language?
topic Sound
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2505.20770